Rogerio Feris

Wei Lin, Leonid Karlinsky, Nina Shvetsova et al. · ibm-research, mit

Large scale Vision-Language (VL) models have shown tremendous success in aligning representations between visual and text modalities. This enables remarkable progress in zero-shot recognition, image generation & editing, and many other exciting tasks. However, VL models tend to over-represent objects while paying much less attention to verbs, and require additional tuning on video data for best zero-shot action recognition performance. While previous work relied on large-scale, fully-annotated data, in this work we propose an unsupervised approach. We adapt a VL model for zero-shot and few-shot action recognition using a collection of unlabeled videos and an unpaired action dictionary. Based on that, we leverage Large Language Models and VL models to build a text bag for each unlabeled video via matching, text expansion and captioning. We use those bags in a Multiple Instance Learning setup to adapt an image-text backbone to video data. Although finetuned on unlabeled video data, our resulting models demonstrate high transferability to numerous unseen zero-shot downstream tasks, improving the base VL model performance by up to 14\%, and even comparing favorably to fully-supervised baselines in both zero-shot and few-shot video recognition transfer. The code will be released later at \url{https://github.com/wlin-at/MAXI}.

Andrew Rouditchenko, Yung-Sung Chuang, Nina Shvetsova et al. · ibm-research, mit

Multilingual text-video retrieval methods have improved significantly in recent years, but the performance for other languages lags behind English. We propose a Cross-Lingual Cross-Modal Knowledge Distillation method to improve multilingual text-video retrieval. Inspired by the fact that English text-video retrieval outperforms other languages, we train a student model using input text in different languages to match the cross-modal predictions from teacher models using input text in English. We propose a cross entropy based objective which forces the distribution over the student's text-video similarity scores to be similar to those of the teacher models. We introduce a new multilingual video dataset, Multi-YouCook2, by translating the English captions in the YouCook2 video dataset to 8 other languages. Our method improves multilingual text-video retrieval performance on Multi-YouCook2 and several other datasets such as Multi-MSRVTT and VATEX. We also conducted an analysis on the effectiveness of different multilingual text models as teachers. The code, models, and dataset are available at https://github.com/roudimit/c2kd.

James Seale Smith, Leonid Karlinsky, Vyshnavi Gutta et al.

Computer vision models suffer from a phenomenon known as catastrophic forgetting when learning novel concepts from continuously shifting training data. Typical solutions for this continual learning problem require extensive rehearsal of previously seen data, which increases memory costs and may violate data privacy. Recently, the emergence of large-scale pre-trained vision transformer models has enabled prompting approaches as an alternative to data-rehearsal. These approaches rely on a key-query mechanism to generate prompts and have been found to be highly resistant to catastrophic forgetting in the well-established rehearsal-free continual learning setting. However, the key mechanism of these methods is not trained end-to-end with the task sequence. Our experiments show that this leads to a reduction in their plasticity, hence sacrificing new task accuracy, and inability to benefit from expanded parameter capacity. We instead propose to learn a set of prompt components which are assembled with input-conditioned weights to produce input-conditioned prompts, resulting in a novel attention-based end-to-end key-query scheme. Our experiments show that we outperform the current SOTA method DualPrompt on established benchmarks by as much as 4.5% in average final accuracy. We also outperform the state of art by as much as 4.4% accuracy on a continual learning benchmark which contains both class-incremental and domain-incremental task shifts, corresponding to many practical settings. Our code is available at https://github.com/GT-RIPL/CODA-Prompt

Peihao Wang, Rameswar Panda, Lucas Torroba Hennigen et al. · mit

Scaling transformers has led to significant breakthroughs in many domains, leading to a paradigm in which larger versions of existing models are trained and released on a periodic basis. New instances of such models are typically trained completely from scratch, despite the fact that they are often just scaled-up versions of their smaller counterparts. How can we use the implicit knowledge in the parameters of smaller, extant models to enable faster training of newer, larger models? This paper describes an approach for accelerating transformer training by learning to grow pretrained transformers, where we learn to linearly map the parameters of the smaller model to initialize the larger model. For tractable learning, we factorize the linear transformation as a composition of (linear) width- and depth-growth operators, and further employ a Kronecker factorization of these growth operators to encode architectural knowledge. Extensive experiments across both language and vision transformers demonstrate that our learned Linear Growth Operator (LiGO) can save up to 50% computational cost of training from scratch, while also consistently outperforming strong baselines that also reuse smaller pretrained models to initialize larger models.

Manel Baradad, Chun-Fu Chen, Jonas Wulff et al. · mit

Learning image representations using synthetic data allows training neural networks without some of the concerns associated with real images, such as privacy and bias. Existing work focuses on a handful of curated generative processes which require expert knowledge to design, making it hard to scale up. To overcome this, we propose training with a large dataset of twenty-one thousand programs, each one generating a diverse set of synthetic images. These programs are short code snippets, which are easy to modify and fast to execute using OpenGL. The proposed dataset can be used for both supervised and unsupervised representation learning, and reduces the gap between pre-training with real and procedurally generated images by 38%.

James Seale Smith, Paola Cascante-Bonilla, Assaf Arbelle et al.

Recently, large-scale pre-trained Vision-and-Language (VL) foundation models have demonstrated remarkable capabilities in many zero-shot downstream tasks, achieving competitive results for recognizing objects defined by as little as short text prompts. However, it has also been shown that VL models are still brittle in Structured VL Concept (SVLC) reasoning, such as the ability to recognize object attributes, states, and inter-object relations. This leads to reasoning mistakes, which need to be corrected as they occur by teaching VL models the missing SVLC skills; often this must be done using private data where the issue was found, which naturally leads to a data-free continual (no task-id) VL learning setting. In this work, we introduce the first Continual Data-Free Structured VL Concepts Learning (ConStruct-VL) benchmark and show it is challenging for many existing data-free CL strategies. We, therefore, propose a data-free method comprised of a new approach of Adversarial Pseudo-Replay (APR) which generates adversarial reminders of past tasks from past task models. To use this method efficiently, we also propose a continual parameter-efficient Layered-LoRA (LaLo) neural architecture allowing no-memory-cost access to all past models at train time. We show this approach outperforms all data-free methods by as much as ~7% while even matching some levels of experience-replay (prohibitive for applications where data-privacy must be preserved). Our code is publicly available at https://github.com/jamessealesmith/ConStruct-VL

Brian Chen, Nina Shvetsova, Andrew Rouditchenko et al. · ibm-research, mit

Spatio-temporal grounding describes the task of localizing events in space and time, e.g., in video data, based on verbal descriptions only. Models for this task are usually trained with human-annotated sentences and bounding box supervision. This work addresses this task from a multimodal supervision perspective, proposing a framework for spatio-temporal action grounding trained on loose video and subtitle supervision only, without human annotation. To this end, we combine local representation learning, which focuses on leveraging fine-grained spatial information, with a global representation encoding that captures higher-level representations and incorporates both in a joint approach. To evaluate this challenging task in a real-life setting, a new benchmark dataset is proposed providing dense spatio-temporal grounding annotations in long, untrimmed, multi-action instructional videos for over 5K events. We evaluate the proposed approach and other methods on the proposed and standard downstream tasks showing that our method improves over current baselines in various settings, including spatial, temporal, and untrimmed multi-action spatio-temporal grounding.

Kuniaki Saito, Donghyun Kim, Piotr Teterwak et al.

Building object detectors that are robust to domain shifts is critical for real-world applications. Prior approaches fine-tune a pre-trained backbone and risk overfitting it to in-distribution (ID) data and distorting features useful for out-of-distribution (OOD) generalization. We propose to use Relative Gradient Norm (RGN) as a way to measure the vulnerability of a backbone to feature distortion, and show that high RGN is indeed correlated with lower OOD performance. Our analysis of RGN yields interesting findings: some backbones lose OOD robustness during fine-tuning, but others gain robustness because their architecture prevents the parameters from changing too much from the initial model. Given these findings, we present recipes to boost OOD robustness for both types of backbones. Specifically, we investigate regularization and architectural choices for minimizing gradient updates so as to prevent the tuned backbone from losing generalizable features. Our proposed techniques complement each other and show substantial improvements over baselines on diverse architectures and datasets. Code is available at https://github.com/VisionLearningGroup/mind_back.

Howard Zhong, Samarth Mishra, Donghyun Kim et al.

Pre-training on massive video datasets has become essential to achieve high action recognition performance on smaller downstream datasets. However, most large-scale video datasets contain images of people and hence are accompanied with issues related to privacy, ethics, and data protection, often preventing them from being publicly shared for reproducible research. Existing work has attempted to alleviate these problems by blurring faces, downsampling videos, or training on synthetic data. On the other hand, analysis on the transferability of privacy-preserving pre-trained models to downstream tasks has been limited. In this work, we study this problem by first asking the question: can we pre-train models for human action recognition with data that does not include real humans? To this end, we present, for the first time, a benchmark that leverages real-world videos with humans removed and synthetic data containing virtual humans to pre-train a model. We then evaluate the transferability of the representation learned on this data to a diverse set of downstream action recognition benchmarks. Furthermore, we propose a novel pre-training strategy, called Privacy-Preserving MAE-Align, to effectively combine synthetic data and human-removed real data. Our approach outperforms previous baselines by up to 5% and closes the performance gap between human and no-human action recognition representations on downstream tasks, for both linear probing and fine-tuning. Our benchmark, code, and models are available at https://github.com/howardzh01/PPMA .

Jovana Kondic, Pengyuan Li, Dhiraj Joshi et al. · ibm-research

Understanding charts requires models to jointly reason over geometric visual patterns, structured numerical data, and natural language -- a capability where current vision-language models (VLMs) remain limited. We introduce ChartNet, a high-quality, million-scale multimodal dataset designed to advance chart interpretation and reasoning. ChartNet leverages a novel code-guided synthesis pipeline to generate 1.5 million diverse chart samples spanning 24 chart types and 6 plotting libraries. Each sample consists of five aligned components: plotting code, rendered chart image, data table, natural language summary, and question-answering with reasoning, providing fine-grained cross-modal alignment. To capture the full spectrum of chart comprehension, ChartNet additionally includes specialized subsets encompassing human annotated data, real-world data, safety, and grounding. Moreover, a rigorous quality-filtering pipeline ensures visual fidelity, semantic accuracy, and diversity across chart representations. Fine-tuning on ChartNet consistently improves results across benchmarks, demonstrating its utility as large-scale supervision for multimodal models. As the largest open-source dataset of its kind, ChartNet aims to support the development of foundation models with robust and generalizable capabilities for data visualization understanding. The dataset is publicly available at https://huggingface.co/datasets/ibm-granite/ChartNet

Zhen Wang, Rameswar Panda, Leonid Karlinsky et al.

Prompt tuning, in which a base pretrained model is adapted to each task via conditioning on learned prompt vectors, has emerged as a promising approach for efficiently adapting large language models to multiple downstream tasks. However, existing methods typically learn soft prompt vectors from scratch, and it has not been clear how to exploit the rich cross-task knowledge with prompt vectors in a multitask learning setting. We propose multitask prompt tuning (MPT), which first learns a single transferable prompt by distilling knowledge from multiple task-specific source prompts. We then learn multiplicative low rank updates to this shared prompt to efficiently adapt it to each downstream target task. Extensive experiments on 23 NLP datasets demonstrate that our proposed approach outperforms the state-of-the-art methods, including the full finetuning baseline in some cases, despite only tuning 0.035% as many task-specific parameters.

Yi Li, Rameswar Panda, Yoon Kim et al.

Designing better machine translation systems by considering auxiliary inputs such as images has attracted much attention in recent years. While existing methods show promising performance over the conventional text-only translation systems, they typically require paired text and image as input during inference, which limits their applicability to real-world scenarios. In this paper, we introduce a visual hallucination framework, called VALHALLA, which requires only source sentences at inference time and instead uses hallucinated visual representations for multimodal machine translation. In particular, given a source sentence an autoregressive hallucination transformer is used to predict a discrete visual representation from the input text, and the combined text and hallucinated representations are utilized to obtain the target translation. We train the hallucination transformer jointly with the translation transformer using standard backpropagation with cross-entropy losses while being guided by an additional loss that encourages consistency between predictions using either ground-truth or hallucinated visual representations. Extensive experiments on three standard translation datasets with a diverse set of language pairs demonstrate the effectiveness of our approach over both text-only baselines and state-of-the-art methods. Project page: http://www.svcl.ucsd.edu/projects/valhalla.

Sivan Doveh, Assaf Arbelle, Sivan Harary et al.

Vision and Language (VL) models have demonstrated remarkable zero-shot performance in a variety of tasks. However, some aspects of complex language understanding still remain a challenge. We introduce the collective notion of Structured Vision&Language Concepts (SVLC) which includes object attributes, relations, and states which are present in the text and visible in the image. Recent studies have shown that even the best VL models struggle with SVLC. A possible way of fixing this issue is by collecting dedicated datasets for teaching each SVLC type, yet this might be expensive and time-consuming. Instead, we propose a more elegant data-driven approach for enhancing VL models' understanding of SVLCs that makes more effective use of existing VL pre-training datasets and does not require any additional data. While automatic understanding of image structure still remains largely unsolved, language structure is much better modeled and understood, allowing for its effective utilization in teaching VL models. In this paper, we propose various techniques based on language structure understanding that can be used to manipulate the textual part of off-the-shelf paired VL datasets. VL models trained with the updated data exhibit a significant improvement of up to 15% in their SVLC understanding with only a mild degradation in their zero-shot capabilities both when training from scratch or fine-tuning a pre-trained model.

Minglai Yang, Xinyan Velocity Yu, Pengyuan Li et al.

Document parsing and recognition are fundamental capabilities for vision-language models (VLMs) and document processing systems. However, existing Optical Character Recognition (OCR) and document parsing benchmarks are increasingly limited in coverage and difficulty: many focus on common document genres or uniformly sampled pages where modern parsers already perform strongly, while offering limited annotation for expert-domain structures such as chemical formula, music notation, complex tables, and cross-page layouts. We introduce Dr. DocBench, a difficulty-aware benchmark for expert-level document parsing. Built from a large-scale multilingual book corpus, Dr. DocBench spans 52 BISAC subject domains and selects challenging documents through parser-failure-based sampling, targeting cases where multiple state-of-the-art systems struggle. It contains 4,514 annotated pages from long documents averaging around 100 pages, with 65k high-quality page- and block-level annotations for layout, reading order, hierarchical relations, and domain-specific visual contents. Evaluations of pipeline-based parsers and general-purpose VLMs show that strong performance on existing benchmarks does not transfer to our expert-level document parsing. Our analysis reveals substantial failures across subjects, content types, and structural attributes, highlighting Dr. DocBench as a comprehensive testbed for diagnosing and advancing document intelligence.

Paola Cascante-Bonilla, Khaled Shehada, James Seale Smith et al.

Large-scale pre-trained Vision & Language (VL) models have shown remarkable performance in many applications, enabling replacing a fixed set of supported classes with zero-shot open vocabulary reasoning over (almost arbitrary) natural language prompts. However, recent works have uncovered a fundamental weakness of these models. For example, their difficulty to understand Visual Language Concepts (VLC) that go 'beyond nouns' such as the meaning of non-object words (e.g., attributes, actions, relations, states, etc.), or difficulty in performing compositional reasoning such as understanding the significance of the order of the words in a sentence. In this work, we investigate to which extent purely synthetic data could be leveraged to teach these models to overcome such shortcomings without compromising their zero-shot capabilities. We contribute Synthetic Visual Concepts (SyViC) - a million-scale synthetic dataset and data generation codebase allowing to generate additional suitable data to improve VLC understanding and compositional reasoning of VL models. Additionally, we propose a general VL finetuning strategy for effectively leveraging SyViC towards achieving these improvements. Our extensive experiments and ablations on VL-Checklist, Winoground, and ARO benchmarks demonstrate that it is possible to adapt strong pre-trained VL models with synthetic data significantly enhancing their VLC understanding (e.g. by 9.9% on ARO and 4.3% on VL-Checklist) with under 1% drop in their zero-shot accuracy.

Amit Alfassy, Assaf Arbelle, Oshri Halimi et al.

Foundation Models (FMs) have demonstrated unprecedented capabilities including zero-shot learning, high fidelity data synthesis, and out of domain generalization. However, as we show in this paper, FMs still have poor out-of-the-box performance on expert tasks (e.g. retrieval of car manuals technical illustrations from language queries), data for which is either unseen or belonging to a long-tail part of the data distribution of the huge datasets used for FM pre-training. This underlines the necessity to explicitly evaluate and finetune FMs on such expert tasks, arguably ones that appear the most in practical real-world applications. In this paper, we propose a first of its kind FETA benchmark built around the task of teaching FMs to understand technical documentation, via learning to match their graphical illustrations to corresponding language descriptions. Our FETA benchmark focuses on text-to-image and image-to-text retrieval in public car manuals and sales catalogue brochures. FETA is equipped with a procedure for completely automatic annotation extraction (code would be released upon acceptance), allowing easy extension of FETA to more documentation types and application domains in the future. Our automatic annotation leads to an automated performance metric shown to be consistent with metrics computed on human-curated annotations (also released). We provide multiple baselines and analysis of popular FMs on FETA leading to several interesting findings that we believe would be very valuable to the FM community, paving the way towards real-world application of FMs for practical expert tasks currently 'overlooked' by standard benchmarks focusing on common objects.

Bowen Pan, Rameswar Panda, SouYoung Jin et al.

We explore the use of language as a perceptual representation for vision-and-language navigation (VLN), with a focus on low-data settings. Our approach uses off-the-shelf vision systems for image captioning and object detection to convert an agent's egocentric panoramic view at each time step into natural language descriptions. We then finetune a pretrained language model to select an action, based on the current view and the trajectory history, that would best fulfill the navigation instructions. In contrast to the standard setup which adapts a pretrained language model to work directly with continuous visual features from pretrained vision models, our approach instead uses (discrete) language as the perceptual representation. We explore several use cases of our language-based navigation (LangNav) approach on the R2R VLN benchmark: generating synthetic trajectories from a prompted language model (GPT-4) with which to finetune a smaller language model; domain transfer where we transfer a policy learned on one simulated environment (ALFRED) to another (more realistic) environment (R2R); and combining both vision- and language-based representations for VLN. Our approach is found to improve upon baselines that rely on visual features in settings where only a few expert trajectories (10-100) are available, demonstrating the potential of language as a perceptual representation for navigation.

Kaihong Wang, Donghyun Kim, Rogerio Feris et al.

While transformers have greatly boosted performance in semantic segmentation, domain adaptive transformers are not yet well explored. We identify that the domain gap can cause discrepancies in self-attention. Due to this gap, the transformer attends to spurious regions or pixels, which deteriorates accuracy on the target domain. We propose to perform adaptation on attention maps with cross-domain attention layers that share features between the source and the target domains. Specifically, we impose consistency between predictions from cross-domain attention and self-attention modules to encourage similar distribution in the attention and output of the model across domains, i.e., attention-level and output-level alignment. We also enforce consistency in attention maps between different augmented views to further strengthen the attention-based alignment. Combining these two components, our method mitigates the discrepancy in attention maps across domains and further boosts the performance of the transformer under unsupervised domain adaptation settings. Our model outperforms the existing state-of-the-art baseline model on three widely used benchmarks, including GTAV-to-Cityscapes by 1.3 percent point (pp), Synthia-to-Cityscapes by 0.6 pp, and Cityscapes-to-ACDC by 1.1 pp, on average. Additionally, we verify the effectiveness and generalizability of our method through extensive experiments. Our code will be publicly available.

Zexue He, Graeme Blackwood, Rameswar Panda et al.

Pre-training models with large crawled corpora can lead to issues such as toxicity and bias, as well as copyright and privacy concerns. A promising way of alleviating such concerns is to conduct pre-training with synthetic tasks and data, since no real-world information is ingested by the model. Our goal in this paper is to understand the factors that contribute to the effectiveness of pre-training models when using synthetic resources, particularly in the context of neural machine translation. We propose several novel approaches to pre-training translation models that involve different levels of lexical and structural knowledge, including: 1) generating obfuscated data from a large parallel corpus 2) concatenating phrase pairs extracted from a small word-aligned corpus, and 3) generating synthetic parallel data without real human language corpora. Our experiments on multiple language pairs reveal that pre-training benefits can be realized even with high levels of obfuscation or purely synthetic parallel data. We hope the findings from our comprehensive empirical analysis will shed light on understanding what matters for NMT pre-training, as well as pave the way for the development of more efficient and less toxic models.

Junmo Kang, Hongyin Luo, Yada Zhu et al. · gatech

Recent works have demonstrated the effectiveness of self-alignment in which a large language model is aligned to follow general instructions using instructional data generated from the model itself starting from a handful of human-written seeds. Instead of general alignment, in this work, we focus on self-alignment for expert domain specialization (e.g., biomedicine, finance). As a preliminary, we quantitively show the marginal effect that generic instruction-following training has on downstream expert domains' performance. To remedy this, we propose self-specialization - allowing for effective model specialization while achieving cross-task generalization by leveraging only a few labeled seeds. Self-specialization offers a data- and parameter-efficient way of "carving out" an expert model out of a generalist pre-trained LLM. Exploring a variety of popular open large models as a base for specialization, our experimental results in both biomedical and financial domains show that our self-specialized models outperform their base models by a large margin, and even larger models that are generally instruction-tuned or that have been adapted to the target domain by other means.

Matt Stallone, Vaibhav Saxena, Leonid Karlinsky et al.

This paper introduces long-context Granite code models that support effective context windows of up to 128K tokens. Our solution for scaling context length of Granite 3B/8B code models from 2K/4K to 128K consists of a light-weight continual pretraining by gradually increasing its RoPE base frequency with repository-level file packing and length-upsampled long-context data. Additionally, we also release instruction-tuned models with long-context support which are derived by further finetuning the long context base models on a mix of permissively licensed short and long-context instruction-response pairs. While comparing to the original short-context Granite code models, our long-context models achieve significant improvements on long-context tasks without any noticeable performance degradation on regular code completion benchmarks (e.g., HumanEval). We release all our long-context Granite code models under an Apache 2.0 license for both research and commercial use.

M. Jehanzeb Mirza, Leonid Karlinsky, Wei Lin et al.

Vision and Language Models (VLMs), such as CLIP, have enabled visual recognition of a potentially unlimited set of categories described by text prompts. However, for the best visual recognition performance, these models still require tuning to better fit the data distributions of the downstream tasks, in order to overcome the domain shift from the web-based pre-training data. Recently, it has been shown that it is possible to effectively tune VLMs without any paired data, and in particular to effectively improve VLMs visual recognition performance using text-only training data generated by Large Language Models (LLMs). In this paper, we dive deeper into this exciting text-only VLM training approach and explore ways it can be significantly further improved taking the specifics of the downstream task into account when sampling text data from LLMs. In particular, compared to the SOTA text-only VLM training approach, we demonstrate up to 8.4% performance improvement in (cross) domain-specific adaptation, up to 8.7% improvement in fine-grained recognition, and 3.1% overall average improvement in zero-shot classification compared to strong baselines.

Kelvin Li, Chuyi Shang, Leonid Karlinsky et al.

While Large Multimodal Models (LMMs) have made significant progress, they remain largely text-centric, relying on language as their core reasoning modality. As a result, they are limited in their ability to handle reasoning tasks that are predominantly visual. Recent approaches have sought to address this by supervising intermediate visual steps with helper images, depth maps, or image crops. However, these strategies impose restrictive priors on what "useful" visual abstractions look like, add heavy annotation costs, and struggle to generalize across tasks. To address this critical limitation, we propose a task-agnostic mechanism that trains LMMs to discover and use visual reasoning tokens without explicit supervision. These tokens attend globally and re-encode the image in a task-adaptive way, enabling the model to extract relevant visual information without hand-crafted supervision. Our approach outperforms direct fine-tuning and achieves state-of-the-art results on a diverse range of vision-centric tasks -- including those where intermediate abstractions are hard to specify -- while also generalizing to multi-task instruction tuning.

Ziyun Zeng, Hang Hua, Bocheng Zou et al.

Recent GUI agents have made substantial progress in visual grounding and action prediction, yet they remain brittle in long-horizon tasks that require maintaining task state across many interface transitions. Existing agents typically rely on raw history replay or text-only memory, which either overwhelms the model with redundant screenshots or discards localized visual evidence needed for future decisions. To address these limitations, we introduce \textbf{MementoGUI}, a plug-in agentic memory framework that equips MLLM-based GUI agents with \textbf{MementoCore}, a learned controller for online memory selection, compression, and retrieval. Rather than treating interaction history as a fixed context, MementoGUI formulates long-horizon GUI control as an online memory-control problem: working memory selectively preserves task-relevant interface events with textual summaries and ROI-level visual evidence, while episodic memory retrieves reusable past trajectories through learned relevance selection. MementoCore modularizes memory control into specialized operators for step processing, memory compression, episodic writing, and episodic selection, enabling plug-in memory augmentation without finetuning the GUI agent backbone. We further develop a scalable data curation pipeline that converts computer-use trajectories into memory-controller training data, introduce \textbf{MementoGUI-Bench} for evaluating long-horizon decision-making in GUI agents, and design MLLM-based metrics for semantic action matching, task progress, and memory consistency. Experiments on GUI-Odyssey, MM-Mind2Web, and MementoGUI-Bench show that MementoGUI consistently improves GUI agents over no-history, history-replay, and text-only memory baselines, with larger MementoCore backbones further strengthening memory-augmented GUI control.

Edson Araujo, Saurabhchand Bhati, M. Jehanzeb Mirza et al.

Recent advances in reasoning models have shown remarkable progress in text-based domains, but transferring those capabilities to multimodal settings, e.g., to allow reasoning over audio-visual data, still remains a challenge, in part because of the limited availability of high-quality reasoning data in targeted multimodal combinations. To address this problem, we introduce AVRT, a novel framework that generates high-quality audio-visual reasoning traces from single-modality teacher models. We generate independent vision- and audio-reasoning traces via models specialized to reason over their respective modalities and merge the resulting traces with an LLM merger model. The resulting multimodal traces are used in a supervised fine-tuning (SFT) cold start to adapt the target model to audio-visual reasoning traces first, before training it in a second reinforcement learning stage on larger-scale data. Evaluated on seven audio-visual and audio benchmarks, our 3B and 7B parameter models achieve state-of-the-art results among models of comparable size including OmniBench and DailyOmni for audio-visual and MMAR for audio-only reasoning, showing that cross-modal training also transfers to single-modality tasks and establishing a new training pipeline for multimodal reasoning models.

Brandon Huang, Hang Hua, Zhuoran Yu et al.

While Vision-language models (VLMs) have demonstrated remarkable performance across multi-modal tasks, their choice of vision encoders presents a fundamental weakness: their low-level features lack the robust structural and spatial information essential for document understanding and web agents. To bridge this gap, we introduce DAVE, a vision encoder purpose-built for VLMs and tailored for these tasks. Our training pipeline is designed to leverage abundant unlabeled data to bypass the need for costly large-scale annotations for document and web images. We begin with a self-supervised pretraining stage on unlabeled images, followed by a supervised autoregressive pretraining stage, where the model learns tasks like parsing and localization from limited, high-quality data. Within the supervised stage, we adopt two strategies to improve our encoder's alignment with both general visual knowledge and diverse document and web agentic tasks: (i) We introduce a novel model-merging scheme, combining encoders trained with different text decoders to ensure broad compatibility with different web agentic architectures. (ii) We use ensemble training to fuse features from pretrained generalist encoders (e.g., SigLIP2) with our own document and web-specific representations. Extensive experiments on classic document tasks, VQAs, web localization, and agent-based benchmarks validate the effectiveness of our approach, establishing DAVE as a strong vision encoder for document and web applications.

Videet Mehta, Liming Wang, Hilde Kuehne et al.

Large audio-language models (LALMs) exhibit strong zero-shot capabilities in multiple downstream tasks, such as audio question answering (AQA) and abstract reasoning; however, these models still lag behind specialized models for certain discriminative tasks (e.g., audio classification). Recent studies show that sparse subsets of attention heads within an LALM can serve as strong discriminative feature extractors for downstream tasks such as classification via simple voting schemes. However, these methods assign uniform weights to all selected heads, implicitly assuming that each head contributes equally across all semantic categories. In this work, we propose Class-Conditional Sparse Attention Vectors for Large Audio-Language Models, a few-shot classification method that learns class-dependent importance weights over attention heads. This formulation allows individual heads to specialize in distinct semantic categories and to contribute to ensemble predictions proportionally to their estimated reliability. Experiments on multiple few-shot audio and audiovisual classification benchmarks and tasks demonstrate that our method consistently outperforms state-of-the-art uniform voting-based approaches by up to 14.52%, 1.53%, 8.35% absolute gains for audio classification, audio-visual classification, and spoofing detection respectively.

Yu Wang, Dmitry Krotov, Yuanzhe Hu et al.

Equipping large language models (LLMs) with latent-space memory has attracted increasing attention as they can extend the context window of existing language models. However, retaining information from the distant past remains a challenge. For example, MemoryLLM (Wang et al., 2024a), as a representative work with latent-space memory, compresses past information into hidden states across all layers, forming a memory pool of 1B parameters. While effective for sequence lengths up to 16k tokens, it struggles to retain knowledge beyond 20k tokens. In this work, we address this limitation by introducing M+, a memory-augmented model based on MemoryLLM that significantly enhances long-term information retention. M+ integrates a long-term memory mechanism with a co-trained retriever, dynamically retrieving relevant information during text generation. We evaluate M+ on diverse benchmarks, including long-context understanding and knowledge retention tasks. Experimental results show that M+ significantly outperforms MemoryLLM and recent strong baselines, extending knowledge retention from under 20k to over 160k tokens with similar GPU memory overhead. We open-source our code at https://github.com/wangyu-ustc/MemoryLLM

Granite Vision Team, Leonid Karlinsky, Assaf Arbelle et al.

We introduce Granite Vision, a lightweight large language model with vision capabilities, specifically designed to excel in enterprise use cases, particularly in visual document understanding. Our model is trained on a comprehensive instruction-following dataset, including document-related tasks, such as content extraction from tables, charts, diagrams, sketches, and infographics, as well as general image tasks. The architecture of Granite Vision is centered around visual modality alignment with a decoder-only, 2 billion parameter Granite large language model. Additionally, we introduce a dedicated safety classification approach in test-time that leverages a sparse set of attention vectors to identify potential harmful inputs. Despite its lightweight architecture, Granite Vision achieves strong results in standard benchmarks related to visual document understanding, as well as on the LiveXiv benchmark, which is designed to avoid test set contamination by using a constantly updated corpus of recently published Arxiv papers. We are releasing the model under the Apache-2 license, allowing for both research and commercial use, while offering complete visibility into the training data and other relevant details. See https://huggingface.co/ibm-granite/ for model weights.

Soumya Shamarao Jahagirdar, Edson Araujo, Anna Kukleva et al.

Recent video reasoning models have shown strong results on temporal and multimodal understanding, yet they depend on large-scale supervised data and multi-stage training pipelines, making them costly to train and difficult to adapt to new domains. In this work, we leverage the paradigm of Test-Time Reinforcement Learning on video-language data to allow for adapting a pretrained model to incoming video samples at test-time without explicit labels. The proposed test-time adaptation for video approach (TTA-Vid) combines two components that work simultaneously: (1) a test-time adaptation that performs step-by-step reasoning at inference time on multiple frame subsets. We then use a batch-aware frequency-based reward computed across different frame subsets as pseudo ground truth to update the model. It shows that the resulting model trained on a single batch or even a single sample from a dataset, is able to generalize at test-time to the whole dataset and even across datasets. Because the adaptation occurs entirely at test time, our method requires no ground-truth annotations or dedicated training splits. Additionally, we propose a multi-armed bandit strategy for adaptive frame selection that learns to prioritize informative frames, guided by the same reward formulation. Our evaluation shows that TTA-Vid yields consistent improvements across various video reasoning tasks and is able to outperform current state-of-the-art methods trained on large-scale data. This highlights the potential of test-time reinforcement learning for temporal multimodal understanding.

Saurabhchand Bhati, Samuel Thomas, Hilde Kuehne et al.

Large Audio Language Models (LALMs) demonstrate impressive performance across diverse tasks, ranging from speech recognition to general audio understanding. However, their scalability is limited by the quadratic complexity of attention and the high token rates of audio signals. These challenges make it difficult to extend LALMs to long-form audio and to deploy them on resource-constrained platforms such as edge devices. In this paper, we explore techniques such as unsupervised segmentation, uniform average pooling, etc., to reduce the number of audio tokens generated by the LALM's audio encoder but before they are consumed by the LLM decoder. To mitigate potential performance degradation introduced by the compressed representations, we employ low-rank adapters to finetune the model. We evaluate our proposed models on two tasks, automatic speech recognition and speech-to-speech translation tasks, that are dependent on effectively uncovering the underlying lexical content of the input signal and study the effect of downsampling on these tasks. Experimental results show that compressed LALMs can achieve performance closer to frame-level LALMs while reducing the input audio token count upto three times before the LLM backbone.

Jacob Hansen, Wei Lin, Junmo Kang et al.

Visual Instruction Tuning (VisIT) data, commonly available as human-assistant conversations with images interleaved in the human turns, are currently the most widespread vehicle for aligning strong LLMs to understand visual inputs, converting them to strong LMMs. While many VisIT datasets are available, most are constructed using ad-hoc techniques developed independently by different groups. They are often poorly documented, lack reproducible code, and rely on paid, closed-source model APIs such as GPT-4, Gemini, or Claude to convert image metadata (labels) into VisIT instructions. This leads to high costs and makes it challenging to scale, enhance quality, or generate VisIT data for new datasets. In this work, we address these challenges and propose an open and unified recipe and approach,~\textbf{\method}, for converting available metadata to VisIT instructions using open LLMs. Our multi-stage \method features an efficient framework for metadata grouping, quality control, data and prompt organization, and conversation sampling. We show that our approach can reproduce or enhance the data quality of available VisIT datasets when applied to the same image data and metadata sources, improving GPT-4 generated VisIT instructions by ~3\% on average and up to 12\% on individual benchmarks using open models, such as Gemma 2 27B and LLaMa 3.1 70B. Additionally, our approach enables effective performance scaling - both in quantity and quality - by enhancing the resulting LMM performance across a wide range of benchmarks. We also analyze the impact of various factors, including conversation format, base model selection, and resampling strategies. Our code, which supports the reproduction of equal or higher-quality VisIT datasets and facilities future metadata-to-VisIT data conversion for niche domains, is released at https://github.com/jacob-hansen/Instructify.

Sarthak Kumar Maharana, Baoming Zhang, Leonid Karlinsky et al.

Although open-vocabulary classification models like Contrastive Language Image Pretraining (CLIP) have demonstrated strong zero-shot learning capabilities, their robustness to common image corruptions remains poorly understood. Through extensive experiments, we show that zero-shot CLIP lacks robustness to common image corruptions during test-time, necessitating the adaptation of CLIP to unlabeled corrupted images using test-time adaptation (TTA). However, we found that existing TTA methods have severe limitations in adapting CLIP due to their unimodal nature. To address these limitations, we propose $\texttt{BATCLIP}$, a bimodal $\textbf{online}$ TTA method designed to improve CLIP's robustness to common image corruptions. The key insight of our approach is not only to adapt the visual encoders for improving image features but also to strengthen the alignment between image and text features by promoting a stronger association between the image class prototype, computed using pseudo-labels, and the corresponding text feature. We evaluate our approach on benchmark image corruption datasets and achieve state-of-the-art results in online TTA for CLIP. Furthermore, we evaluate our proposed TTA approach on various domain generalization datasets to demonstrate its generalization capabilities. Our code is available at https://github.com/sarthaxxxxx/BATCLIP

Jovana Kondic, Pengyuan Li, Dhiraj Joshi et al.

Chart-to-code reconstruction -- the task of recovering executable plotting scripts from chart images -- provides important insights into a model's ability to ground data visualizations in precise, machine-readable form. Yet many existing multimodal benchmarks largely focus primarily on answering questions about charts or summarizing them. To bridge this gap, we present ChartGen, a fully-automated pipeline for code-guided synthetic chart generation. Starting from seed chart images, ChartGen (i) prompts a vision-language model (VLM) to reconstruct each image into a python script, and (ii) iteratively augments that script with a code-oriented large language model (LLM). Using ChartGen, we create 222.5K unique chart-image code pairs from 13K seed chart images, and present an open-source synthetic chart dataset covering 27 chart types, 11 plotting libraries, and multiple data modalities (image, code, text, CSV, DocTags). From this corpus, we curate a held-out chart-to-code evaluation subset of 4.3K chart image-code pairs, and evaluate six open-weight VLMs (3B - 26B parameters), highlighting substantial room for progress. We release the pipeline, prompts, and the dataset to help accelerate efforts towards robust chart understanding and vision-conditioned code generation: https://github.com/SD122025/ChartGen/

Jiachen Li, Bowen Cheng, Rogerio Feris et al.

Current anchor-free object detectors are quite simple and effective yet lack accurate label assignment methods, which limits their potential in competing with classic anchor-based models that are supported by well-designed assignment methods based on the Intersection-over-Union~(IoU) metric. In this paper, we present \textbf{Pseudo-Intersection-over-Union~(Pseudo-IoU)}: a simple metric that brings more standardized and accurate assignment rule into anchor-free object detection frameworks without any additional computational cost or extra parameters for training and testing, making it possible to further improve anchor-free object detection by utilizing training samples of good quality under effective assignment rules that have been previously applied in anchor-based methods. By incorporating Pseudo-IoU metric into an end-to-end single-stage anchor-free object detection framework, we observe consistent improvements in their performance on general object detection benchmarks such as PASCAL VOC and MSCOCO. Our method (single-model and single-scale) also achieves comparable performance to other recent state-of-the-art anchor-free methods without bells and whistles. Our code is based on mmdetection toolbox and will be made publicly available at https://github.com/SHI-Labs/Pseudo-IoU-for-Anchor-Free-Object-Detection.

Chun-Fu Chen, Rameswar Panda, Kandan Ramakrishnan et al.

In recent years, a number of approaches based on 2D or 3D convolutional neural networks (CNN) have emerged for video action recognition, achieving state-of-the-art results on several large-scale benchmark datasets. In this paper, we carry out in-depth comparative analysis to better understand the differences between these approaches and the progress made by them. To this end, we develop an unified framework for both 2D-CNN and 3D-CNN action models, which enables us to remove bells and whistles and provides a common ground for fair comparison. We then conduct an effort towards a large-scale analysis involving over 300 action recognition models. Our comprehensive analysis reveals that a) a significant leap is made in efficiency for action recognition, but not in accuracy; b) 2D-CNN and 3D-CNN models behave similarly in terms of spatio-temporal representation abilities and transferability. Our codes are available at https://github.com/IBM/action-recognition-pytorch.

Aadarsh Sahoo, Ankit Singh, Rameswar Panda et al.

Supervised deep learning methods are enjoying enormous success in many practical applications of computer vision and have the potential to revolutionize robotics. However, the marked performance degradation to biases and imbalanced data questions the reliability of these methods. In this work we address these questions from the perspective of dataset imbalance resulting out of severe under-representation of annotated training data for certain classes and its effect on both deep classification and generation methods. We introduce a joint dataset repairment strategy by combining a neural network classifier with Generative Adversarial Networks (GAN) that makes up for the deficit of training examples from the under-representated class by producing additional training examples. We show that the combined training helps to improve the robustness of both the classifier and the GAN against severe class imbalance. We show the effectiveness of our proposed approach on three very different datasets with different degrees of imbalance in them. The code is available at https://github.com/AadSah/ImbalanceCycleGAN .

Zhiqiang Tang, Yunhe Gao, Leonid Karlinsky et al.

Data augmentation is one of the most important tools in training modern deep neural networks. Recently, great advances have been made in searching for optimal augmentation policies in the image classification domain. However, two key points related to data augmentation remain uncovered by the current methods. First is that most if not all modern augmentation search methods are offline and learning policies are isolated from their usage. The learned policies are mostly constant throughout the training process and are not adapted to the current training model state. Second, the policies rely on class-preserving image processing functions. Hence applying current offline methods to new tasks may require domain knowledge to specify such kind of operations. In this work, we offer an orthogonal online data augmentation scheme together with three new augmentation networks, co-trained with the target learning task. It is both more efficient, in the sense that it does not require expensive offline training when entering a new domain, and more adaptive as it adapts to the learner state. Our augmentation networks require less domain knowledge and are easily applicable to new tasks. Extensive experiments demonstrate that the proposed scheme alone performs on par with the state-of-the-art offline data augmentation methods, as well as improving upon the state-of-the-art in combination with those methods. Code is available at https://github.com/zhiqiangdon/online-augment .

Bowen Cheng, Yunchao Wei, Rogerio Feris et al.

In this paper, we analyze failure cases of state-of-the-art detectors and observe that most hard false positives result from classification instead of localization and they have a large negative impact on the performance of object detectors. We conjecture there are three factors: (1) Shared feature representation is not optimal due to the mismatched goals of feature learning for classification and localization; (2) multi-task learning helps, yet optimization of the multi-task loss may result in sub-optimal for individual tasks; (3) large receptive field for different scales leads to redundant context information for small objects. We demonstrate the potential of detector classification power by a simple, effective, and widely-applicable Decoupled Classification Refinement (DCR) network. In particular, DCR places a separate classification network in parallel with the localization network (base detector). With ROI Pooling placed on the early stage of the classification network, we enforce an adaptive receptive field in DCR. During training, DCR samples hard false positives from the base detector and trains a strong classifier to refine classification results. During testing, DCR refines all boxes from the base detector. Experiments show competitive results on PASCAL VOC and COCO without any bells and whistles. Our codes are available at: https://github.com/bowenc0221/Decoupled-Classification-Refinement.

Chun-Fu Chen, Quanfu Fan, Neil Mallinar et al.

In this paper, we propose a novel Convolutional Neural Network (CNN) architecture for learning multi-scale feature representations with good tradeoffs between speed and accuracy. This is achieved by using a multi-branch network, which has different computational complexity at different branches. Through frequent merging of features from branches at distinct scales, our model obtains multi-scale features while using less computation. The proposed approach demonstrates improvement of model efficiency and performance on both object recognition and speech recognition tasks,using popular architectures including ResNet and ResNeXt. For object recognition, our approach reduces computation by 33% on object recognition while improving accuracy with 0.9%. Furthermore, our model surpasses state-of-the-art CNN acceleration approaches by a large margin in accuracy and FLOPs reduction. On the task of speech recognition, our proposed multi-scale CNNs save 30% FLOPs with slightly better word error rates, showing good generalization across domains. The codes are available at https://github.com/IBM/BigLittleNet

Zhiqiang Shen, Honghui Shi, Jiahui Yu et al.

In this paper, we present a simple and parameter-efficient drop-in module for one-stage object detectors like SSD when learning from scratch (i.e., without pre-trained models). We call our module GFR (Gated Feature Reuse), which exhibits two main advantages. First, we introduce a novel gate-controlled prediction strategy enabled by Squeeze-and-Excitation to adaptively enhance or attenuate supervision at different scales based on the input object size. As a result, our model is more effective in detecting diverse sizes of objects. Second, we propose a feature-pyramids structure to squeeze rich spatial and semantic features into a single prediction layer, which strengthens feature representation and reduces the number of parameters to learn. We apply the proposed structure on DSOD and SSD detection frameworks, and evaluate the performance on PASCAL VOC 2007, 2012 and COCO datasets. With fewer model parameters, GFR-DSOD outperforms the baseline DSOD by 1.4%, 1.1%, 1.7% and 0.6%, respectively. GFR-SSD also outperforms the original SSD and SSD with dense prediction by 3.6% and 2.8% on VOC 2007 dataset. Code is available at: https://github.com/szq0214/GFR-DSOD .

Shuangfei Zhai, Hui Wu, Abhishek Kumar et al.

Feature pooling layers (e.g., max pooling) in convolutional neural networks (CNNs) serve the dual purpose of providing increasingly abstract representations as well as yielding computational savings in subsequent convolutional layers. We view the pooling operation in CNNs as a two-step procedure: first, a pooling window (e.g., $2\times 2$) slides over the feature map with stride one which leaves the spatial resolution intact, and second, downsampling is performed by selecting one pixel from each non-overlapping pooling window in an often uniform and deterministic (e.g., top-left) manner. Our starting point in this work is the observation that this regularly spaced downsampling arising from non-overlapping windows, although intuitive from a signal processing perspective (which has the goal of signal reconstruction), is not necessarily optimal for \emph{learning} (where the goal is to generalize). We study this aspect and propose a novel pooling strategy with stochastic spatial sampling (S3Pool), where the regular downsampling is replaced by a more general stochastic version. We observe that this general stochasticity acts as a strong regularizer, and can also be seen as doing implicit data augmentation by introducing distortions in the feature maps. We further introduce a mechanism to control the amount of distortion to suit different datasets and architectures. To demonstrate the effectiveness of the proposed approach, we perform extensive experiments on several popular image classification benchmarks, observing excellent improvements over baseline models. Experimental code is available at https://github.com/Shuangfei/s3pool.

Shuangfei Zhai, Yu Cheng, Rogerio Feris et al.

In this paper, we study deep generative models for effective unsupervised learning. We propose VGAN, which works by minimizing a variational lower bound of the negative log likelihood (NLL) of an energy based model (EBM), where the model density $p(\mathbf{x})$ is approximated by a variational distribution $q(\mathbf{x})$ that is easy to sample from. The training of VGAN takes a two step procedure: given $p(\mathbf{x})$, $q(\mathbf{x})$ is updated to maximize the lower bound; $p(\mathbf{x})$ is then updated one step with samples drawn from $q(\mathbf{x})$ to decrease the lower bound. VGAN is inspired by the generative adversarial networks (GANs), where $p(\mathbf{x})$ corresponds to the discriminator and $q(\mathbf{x})$ corresponds to the generator, but with several notable differences. We hence name our model variational GANs (VGANs). VGAN provides a practical solution to training deep EBMs in high dimensional space, by eliminating the need of MCMC sampling. From this view, we are also able to identify causes to the difficulty of training GANs and propose viable solutions. \footnote{Experimental code is available at https://github.com/Shuangfei/vgan}

Zexue He, Leonid Karlinsky, Donghyun Kim et al.

Large Language Models (LLMs) struggle to handle long input sequences due to high memory and runtime costs. Memory-augmented models have emerged as a promising solution to this problem, but current methods are hindered by limited memory capacity and require costly re-training to integrate with a new LLM. In this work, we introduce an associative memory module which can be coupled to any pre-trained (frozen) attention-based LLM without re-training, enabling it to handle arbitrarily long input sequences. Unlike previous methods, our associative memory module consolidates representations of individual tokens into a non-parametric distribution model, dynamically managed by properly balancing the novelty and recency of the incoming data. By retrieving information from this consolidated associative memory, the base LLM can achieve significant (up to 29.7% on Arxiv) perplexity reduction in long-context modeling compared to other baselines evaluated on standard benchmarks. This architecture, which we call CAMELoT (Consolidated Associative Memory Enhanced Long Transformer), demonstrates superior performance even with a tiny context window of 128 tokens, and also enables improved in-context learning with a much larger set of demonstrations.

James Seale Smith, Lazar Valkov, Shaunak Halbe et al.

Foundation Models (FMs) have become the hallmark of modern AI, however, these models are trained on massive data, leading to financially expensive training. Updating FMs as new data becomes available is important, however, can lead to `catastrophic forgetting', where models underperform on tasks related to data sub-populations observed too long ago. This continual learning (CL) phenomenon has been extensively studied, but primarily in a setting where only a small amount of past data can be stored. We advocate for the paradigm where memory is abundant, allowing us to keep all previous data, but computational resources are limited. In this setting, traditional replay-based CL approaches are outperformed by a simple baseline which replays past data selected uniformly at random, indicating that this setting necessitates a new approach. We address this by introducing a framework of adaptive memory replay for continual learning, where sampling of past data is phrased as a multi-armed bandit problem. We utilize Bolzmann sampling to derive a method which dynamically selects past data for training conditioned on the current task, assuming full data access and emphasizing training efficiency. Through extensive evaluations on both vision and language pre-training tasks, we demonstrate the effectiveness of our approach, which maintains high performance while reducing forgetting by up to 10% at no training efficiency cost.

Aaron Baughman, Stephen Hammer, Rahul Agarwal et al.

We address the problem of scaling up the production of media content, including commentary and personalized news stories, for large-scale sports and music events worldwide. Our approach relies on generative AI models to transform a large volume of multimodal data (e.g., videos, articles, real-time scoring feeds, statistics, and fact sheets) into coherent and fluent text. Based on this approach, we introduce, for the first time, an AI commentary system, which was deployed to produce automated narrations for highlight packages at the 2023 US Open, Wimbledon, and Masters tournaments. In the same vein, our solution was extended to create personalized content for ESPN Fantasy Football and stories about music artists for the Grammy awards. These applications were built using a common software architecture achieved a 15x speed improvement with an average Rouge-L of 82.00 and perplexity of 6.6. Our work was successfully deployed at the aforementioned events, supporting 90 million fans around the world with 8 billion page views, continuously pushing the bounds on what is possible at the intersection of sports, entertainment, and AI.

Saurabhchand Bhati, Yuan Gong, Leonid Karlinsky et al.

Large Audio Language Models (LALM) combine the audio perception models and the Large Language Models (LLM) and show a remarkable ability to reason about the input audio, infer the meaning, and understand the intent. However, these systems rely on Transformers which scale quadratically with the input sequence lengths which poses computational challenges in deploying these systems in memory and time-constrained scenarios. Recently, the state-space models (SSMs) have emerged as an alternative to transformer networks. While there have been successful attempts to replace transformer-based audio perception models with state-space ones, state-space-based LALMs remain unexplored. First, we begin by replacing the transformer-based audio perception module and then replace the transformer-based LLM and propose the first state-space-based LALM. Experimental results demonstrate that space-based LALM despite having a significantly lower number of parameters performs competitively with transformer-based LALMs on close-ended tasks on a variety of datasets.

Nasim Borazjanizadeh, Roei Herzig, Eduard Oks et al.

Human reasoning relies on constructing and manipulating mental models -- simplified internal representations of situations used to understand and solve problems. Conceptual diagrams (e.g., a sketch drawn to aid reasoning) externalize these mental models, abstracting irrelevant details to efficiently capture how entities interact. In contrast, Large Language Models (LLMs) and Large MultiModal Models (LMMs) predominantly reason through text, limiting their effectiveness on complex multi-step tasks. In this paper, we propose Visual Thinking, a generalizable framework that enables LMMs to reason through multiple chains of self-generated conceptual diagrams, significantly enhancing their combinatorial planning capabilities. Our approach requires no human input beyond the natural language description of the task. It integrates textual and diagrammatic reasoning within an optimized Graph-of-Thought inference framework, enhanced by beam search and depth-wise backtracking. Evaluated on multiple challenging PDDL planning domains, our method substantially improves LMM performance (e.g., GPT-4o: 35.5% -> 90.2% in Blocksworld) and consistently outperforms text-only search-based inference methods. On more difficult domains with solution depths up to 40, it also surpasses the o1-preview reasoning model (e.g., 16 percentage points improvement in Floor Tiles). These results demonstrate the power of conceptual diagrams as a reasoning medium in LMMs.

Chancharik Mitra, Brandon Huang, Tianning Chai et al.

Generative Large Multimodal Models (LMMs) like LLaVA and Qwen-VL excel at a wide variety of vision-language (VL) tasks. Despite strong performance, LMMs' generative outputs are not specialized for vision-language classification tasks (i.e., tasks with vision-language inputs and discrete labels) such as image classification and multiple-choice VQA. One key challenge in utilizing LMMs for these tasks is the extraction of useful features from generative LMMs. To overcome this, we propose an approach that leverages multimodal feature extraction from the LMM's latent space. Toward this end, we present Sparse Attention Vectors (SAVs) -- a finetuning-free method that leverages sparse attention head activations (fewer than 5% of the heads) in LMMs as strong feature representations. With only few-shot examples, SAVs demonstrate state-of-the-art performance compared to a variety of few-shot and finetuned baselines on a collection of vision-language classification tasks. Our experiments also imply that SAVs can scale in performance with additional examples and generalize to similar tasks, establishing SAVs as both effective and robust multimodal feature representations.

Sivan Doveh, Nimrod Shabtay, Wei Lin et al.

Vision-Language Models (VLMs) have shown remarkable capabilities across diverse visual tasks, including image recognition, video understanding, and Visual Question Answering (VQA) when explicitly trained for these tasks. Despite these advances, we find that present-day VLMs (including the proprietary GPT-4o) lack a fundamental cognitive ability: learning to localize specific objects in a scene by taking into account the context. In this work, we focus on the task of few-shot personalized localization, where a model is given a small set of annotated images (in-context examples) -- each with a category label and bounding box -- and is tasked with localizing the same object type in a query image. Personalized localization can be particularly important in cases of ambiguity of several related objects that can respond to a text or an object that is hard to describe with words. To provoke personalized localization abilities in models, we present a data-centric solution that fine-tunes them using carefully curated data from video object tracking datasets. By leveraging sequences of frames tracking the same object across multiple shots, we simulate instruction-tuning dialogues that promote context awareness. To reinforce this, we introduce a novel regularization technique that replaces object labels with pseudo-names, ensuring the model relies on visual context rather than prior knowledge. Our method significantly enhances the few-shot localization performance of recent VLMs ranging from 7B to 72B in size, without sacrificing generalization, as demonstrated on several benchmarks tailored towards evaluating personalized localization abilities. This work is the first to explore and benchmark personalized few-shot localization for VLMs -- exposing critical weaknesses in present-day VLMs, and laying a foundation for future research in context-driven vision-language applications.