Chen Sun

Ziniu Hu, Ahmet Iscen, Chen Sun et al. · cmu

In this paper, we propose an end-to-end Retrieval-Augmented Visual Language Model (REVEAL) that learns to encode world knowledge into a large-scale memory, and to retrieve from it to answer knowledge-intensive queries. REVEAL consists of four key components: the memory, the encoder, the retriever and the generator. The large-scale memory encodes various sources of multimodal world knowledge (e.g. image-text pairs, question answering pairs, knowledge graph triplets, etc) via a unified encoder. The retriever finds the most relevant knowledge entries in the memory, and the generator fuses the retrieved knowledge with the input query to produce the output. A key novelty in our approach is that the memory, encoder, retriever and generator are all pre-trained end-to-end on a massive amount of data. Furthermore, our approach can use a diverse set of multimodal knowledge sources, which is shown to result in significant gains. We show that REVEAL achieves state-of-the-art results on visual question answering and image captioning.

Xingyi Zhou, Anurag Arnab, Chen Sun et al.

We propose a new task and model for dense video object captioning -- detecting, tracking and captioning trajectories of objects in a video. This task unifies spatial and temporal localization in video, whilst also requiring fine-grained visual understanding that is best described by natural language. We propose a unified model, and demonstrate how our end-to-end approach is more accurate and temporally coherent than a multi-stage pipeline combining state-of-the-art detection, tracking, and captioning models. Moreover, we propose a training strategy based on a mixture of disjoint tasks, which allows us to leverage diverse, large-scale datasets which supervise different parts of our model. Although each pretraining task only provides weak supervision, they are complementary and, when combined, result in noteworthy zero-shot ability and serve as strong initialization for additional finetuning to further improve accuracy. We carefully design new metrics capturing all components of our task, and show how we can repurpose existing video grounding datasets (e.g. VidSTG and VLN) for our new task. We show that our model improves upon a number of strong baselines for this new task. Furthermore, we can apply our model to the task of spatial grounding, outperforming prior state-of-the-art on VidSTG and VLN, without explicitly training for it. Code is available at https://github.com/google-research/scenic/tree/main/scenic/projects/densevoc.

Yunhao Luo, Chen Sun, Joshua B. Tenenbaum et al. · mit

Effective motion planning in high dimensional spaces is a long-standing open problem in robotics. One class of traditional motion planning algorithms corresponds to potential-based motion planning. An advantage of potential based motion planning is composability -- different motion constraints can be easily combined by adding corresponding potentials. However, constructing motion paths from potentials requires solving a global optimization across configuration space potential landscape, which is often prone to local minima. We propose a new approach towards learning potential based motion planning, where we train a neural network to capture and learn an easily optimizable potentials over motion planning trajectories. We illustrate the effectiveness of such approach, significantly outperforming both classical and recent learned motion planning approaches and avoiding issues with local minima. We further illustrate its inherent composability, enabling us to generalize to a multitude of different motion constraints.

Sangnie Bhardwaj, Willie McClinton, Tongzhou Wang et al. · mit

Pre-trained deep image representations are useful for post-training tasks such as classification through transfer learning, image retrieval, and object detection. Data augmentations are a crucial aspect of pre-training robust representations in both supervised and self-supervised settings. Data augmentations explicitly or implicitly promote invariance in the embedding space to the input image transformations. This invariance reduces generalization to those downstream tasks which rely on sensitivity to these particular data augmentations. In this paper, we propose a method of learning representations that are instead equivariant to data augmentations. We achieve this equivariance through the use of steerable representations. Our representations can be manipulated directly in embedding space via learned linear maps. We demonstrate that our resulting steerable and equivariant representations lead to better performance on transfer learning and robustness: e.g. we improve linear probe top-1 accuracy by between 1% to 3% for transfer; and ImageNet-C accuracy by upto 3.4%. We further show that the steerability of our representations provides significant speedup (nearly 50x) for test-time augmentations; by applying a large number of augmentations for out-of-distribution detection, we significantly improve OOD AUC on the ImageNet-C dataset over an invariant representation.

Chen Sun, Nikolas Guggenberger, Supreeth Shastri

Right to be Forgotten (RTBF) in one of the oldest and prominent of the legal data rights. While its legal intention is straight forward (for example, the GDPR describes it in just 417 words), the computing community has found it challenging to implement this in practice. For example, regulators have issued 205 RTBF violations in the first five years of GDPR i.e., an RTBF failure once every 9 days, on average. In this work, we identify the uncertainties and risks in supporting RTBF from a computing perspective. Then, to mitigate these challenges, we propose a two-phase approach that bridges an intrinsic dichotomy between law and computing. We demonstrate the effectiveness of our technique by showing how it could have fully avoided 80% of RTBF violations that occurred in the year-6 of GDPR. We also discover six long-standing practices of computing and data management that have become anti-patterns for RTBF. Finally, to ground our research, we introduce RTBF capability into Elasticsearch, a popular open-source search engine.

Chen Sun, Wannan Yang, Thomas Jiralerspong et al.

In real life, success is often contingent upon multiple critical steps that are distant in time from each other and from the final reward. These critical steps are challenging to identify with traditional reinforcement learning (RL) methods that rely on the Bellman equation for credit assignment. Here, we present a new RL algorithm that uses offline contrastive learning to hone in on these critical steps. This algorithm, which we call Contrastive Retrospection (ConSpec), can be added to any existing RL algorithm. ConSpec learns a set of prototypes for the critical steps in a task by a novel contrastive loss and delivers an intrinsic reward when the current state matches one of the prototypes. The prototypes in ConSpec provide two key benefits for credit assignment: (i) They enable rapid identification of all the critical steps. (ii) They do so in a readily interpretable manner, enabling out-of-distribution generalization when sensory features are altered. Distinct from other contemporary RL approaches to credit assignment, ConSpec takes advantage of the fact that it is easier to retrospectively identify the small set of steps that success is contingent upon (and ignoring other states) than it is to prospectively predict reward at every taken step. ConSpec greatly improves learning in a diverse set of RL tasks. The code is available at the link: https://github.com/sunchipsster1/ConSpec

Arsha Nagrani, Paul Hongsuck Seo, Bryan Seybold et al.

A major challenge in text-video and text-audio retrieval is the lack of large-scale training data. This is unlike image-captioning, where datasets are in the order of millions of samples. To close this gap we propose a new video mining pipeline which involves transferring captions from image captioning datasets to video clips with no additional manual effort. Using this pipeline, we create a new large-scale, weakly labelled audio-video captioning dataset consisting of millions of paired clips and captions. We show that training a multimodal transformed based model on this data achieves competitive performance on video retrieval and video captioning, matching or even outperforming HowTo100M pretraining with 20x fewer clips. We also show that our mined clips are suitable for text-audio pretraining, and achieve state of the art results for the task of audio retrieval.

Medhini Narasimhan, Arsha Nagrani, Chen Sun et al.

YouTube users looking for instructions for a specific task may spend a long time browsing content trying to find the right video that matches their needs. Creating a visual summary (abridged version of a video) provides viewers with a quick overview and massively reduces search time. In this work, we focus on summarizing instructional videos, an under-explored area of video summarization. In comparison to generic videos, instructional videos can be parsed into semantically meaningful segments that correspond to important steps of the demonstrated task. Existing video summarization datasets rely on manual frame-level annotations, making them subjective and limited in size. To overcome this, we first automatically generate pseudo summaries for a corpus of instructional videos by exploiting two key assumptions: (i) relevant steps are likely to appear in multiple videos of the same task (Task Relevance), and (ii) they are more likely to be described by the demonstrator verbally (Cross-Modal Saliency). We propose an instructional video summarization network that combines a context-aware temporal video encoder and a segment scoring transformer. Using pseudo summaries as weak supervision, our network constructs a visual summary for an instructional video given only video and transcribed speech. To evaluate our model, we collect a high-quality test set, WikiHow Summaries, by scraping WikiHow articles that contain video demonstrations and visual depictions of steps allowing us to obtain the ground-truth summaries. We outperform several baselines and a state-of-the-art video summarization model on this new benchmark.

Jean-Pierre Falet, Hae Beom Lee, Nikolay Malkin et al. · mila

We present a new algorithm for amortized inference in sparse probabilistic graphical models (PGMs), which we call $Δ$-amortized inference ($Δ$-AI). Our approach is based on the observation that when the sampling of variables in a PGM is seen as a sequence of actions taken by an agent, sparsity of the PGM enables local credit assignment in the agent's policy learning objective. This yields a local constraint that can be turned into a local loss in the style of generative flow networks (GFlowNets) that enables off-policy training but avoids the need to instantiate all the random variables for each parameter update, thus speeding up training considerably. The $Δ$-AI objective matches the conditional distribution of a variable given its Markov blanket in a tractable learned sampler, which has the structure of a Bayesian network, with the same conditional distribution under the target PGM. As such, the trained sampler recovers marginals and conditional distributions of interest and enables inference of partial subsets of variables. We illustrate $Δ$-AI's effectiveness for sampling from synthetic PGMs and training latent variable models with sparse factor structure.

Zian Wang, Yiming Shu, Zejian Deng et al.

Risk fields offer spatially structured alternatives to scalar safety metrics. However, hand-crafted static risk field models struggle with occlusion and topology-driven propagation. We present DRIFT, a spatiotemporal risk field governed by an advection-diffusion-reaction partial differential equation (PDE), with an optional telegrapher term. DRIFT draws on three sources: anisotropic Gaussian kernels to capture velocity-induced risk, occlusion-aware latent hazards behind large vehicles, and topology-coupled merge-zone conflict pressure. We further introduce field-centric evaluation metrics to complement the existing Surrogate Safety Measures (SSMs), including Lane-Change Risk Differential, Temporal Anticipation Index, Occlusion Sensitivity Index, and Occlusion Response Latency. Experiments on real-world traffic datasets show that DRIFT reduces occlusion response latency and lowers the near-collision rate under occlusion compared with selected baselines in synthetic scenarios.

Xingyi Zhou, Anurag Arnab, Chen Sun et al.

Current state-of-the-art video models process a video clip as a long sequence of spatio-temporal tokens. However, they do not explicitly model objects, their interactions across the video, and instead process all the tokens in the video. In this paper, we investigate how we can use knowledge of objects to design better video models, namely to process fewer tokens and to improve recognition accuracy. This is in contrast to prior works which either drop tokens at the cost of accuracy, or increase accuracy whilst also increasing the computation required. First, we propose an object-guided token sampling strategy that enables us to retain a small fraction of the input tokens with minimal impact on accuracy. And second, we propose an object-aware attention module that enriches our feature representation with object information and improves overall accuracy. Our resulting framework achieves better performance when using fewer tokens than strong baselines. In particular, we match our baseline with 30%, 40%, and 60% of the input tokens on SomethingElse, Something-something v2, and Epic-Kitchens, respectively. When we use our model to process the same number of tokens as our baseline, we improve by 0.6 to 4.2 points on these datasets.

Alexey Gritsenko, Xuehan Xiong, Josip Djolonga et al.

The most performant spatio-temporal action localisation models use external person proposals and complex external memory banks. We propose a fully end-to-end, purely-transformer based model that directly ingests an input video, and outputs tubelets -- a sequence of bounding boxes and the action classes at each frame. Our flexible model can be trained with either sparse bounding-box supervision on individual frames, or full tubelet annotations. And in both cases, it predicts coherent tubelets as the output. Moreover, our end-to-end model requires no additional pre-processing in the form of proposals, or post-processing in terms of non-maximal suppression. We perform extensive ablation experiments, and significantly advance the state-of-the-art results on four different spatio-temporal action localisation benchmarks with both sparse keyframes and full tubelet annotations.

Valentin Gabeur, Paul Hongsuck Seo, Arsha Nagrani et al.

Audio-visual automatic speech recognition (AV-ASR) is an extension of ASR that incorporates visual cues, often from the movements of a speaker's mouth. Unlike works that simply focus on the lip motion, we investigate the contribution of entire visual frames (visual actions, objects, background etc.). This is particularly useful for unconstrained videos, where the speaker is not necessarily visible. To solve this task, we propose a new sequence-to-sequence AudioVisual ASR TrAnsformeR (AVATAR) which is trained end-to-end from spectrograms and full-frame RGB. To prevent the audio stream from dominating training, we propose different word-masking strategies, thereby encouraging our model to pay attention to the visual stream. We demonstrate the contribution of the visual modality on the How2 AV-ASR benchmark, especially in the presence of simulated noise, and show that our model outperforms all other prior work by a large margin. Finally, we also create a new, real-world test bed for AV-ASR called VisSpeech, which demonstrates the contribution of the visual modality under challenging audio conditions.

Ziniu Hu, Ahmet Iscen, Chen Sun et al.

In this paper, we propose an autonomous information seeking visual question answering framework, AVIS. Our method leverages a Large Language Model (LLM) to dynamically strategize the utilization of external tools and to investigate their outputs, thereby acquiring the indispensable knowledge needed to provide answers to the posed questions. Responding to visual questions that necessitate external knowledge, such as "What event is commemorated by the building depicted in this image?", is a complex task. This task presents a combinatorial search space that demands a sequence of actions, including invoking APIs, analyzing their responses, and making informed decisions. We conduct a user study to collect a variety of instances of human decision-making when faced with this task. This data is then used to design a system comprised of three components: an LLM-powered planner that dynamically determines which tool to use next, an LLM-powered reasoner that analyzes and extracts key information from the tool outputs, and a working memory component that retains the acquired information throughout the process. The collected user behavior serves as a guide for our system in two key ways. First, we create a transition graph by analyzing the sequence of decisions made by users. This graph delineates distinct states and confines the set of actions available at each state. Second, we use examples of user decision-making to provide our LLM-powered planner and reasoner with relevant contextual instances, enhancing their capacity to make informed decisions. We show that AVIS achieves state-of-the-art results on knowledge-intensive visual question answering benchmarks such as Infoseek and OK-VQA.

Qi Zhao, Shijie Wang, Ce Zhang et al.

Can we better anticipate an actor's future actions (e.g. mix eggs) by knowing what commonly happens after his/her current action (e.g. crack eggs)? What if we also know the longer-term goal of the actor (e.g. making egg fried rice)? The long-term action anticipation (LTA) task aims to predict an actor's future behavior from video observations in the form of verb and noun sequences, and it is crucial for human-machine interaction. We propose to formulate the LTA task from two perspectives: a bottom-up approach that predicts the next actions autoregressively by modeling temporal dynamics; and a top-down approach that infers the goal of the actor and plans the needed procedure to accomplish the goal. We hypothesize that large language models (LLMs), which have been pretrained on procedure text data (e.g. recipes, how-tos), have the potential to help LTA from both perspectives. It can help provide the prior knowledge on the possible next actions, and infer the goal given the observed part of a procedure, respectively. To leverage the LLMs, we propose a two-stage framework, AntGPT. It first recognizes the actions already performed in the observed videos and then asks an LLM to predict the future actions via conditioned generation, or to infer the goal and plan the whole procedure by chain-of-thought prompting. Empirical results on the Ego4D LTA v1 and v2 benchmarks, EPIC-Kitchens-55, as well as EGTEA GAZE+ demonstrate the effectiveness of our proposed approach. AntGPT achieves state-of-the-art performance on all above benchmarks, and can successfully infer the goal and thus perform goal-conditioned "counterfactual" prediction via qualitative analysis. Code and model will be released at https://brown-palm.github.io/AntGPT

Anurag Arnab, Xuehan Xiong, Alexey Gritsenko et al.

Transfer learning is the predominant paradigm for training deep networks on small target datasets. Models are typically pretrained on large ``upstream'' datasets for classification, as such labels are easy to collect, and then finetuned on ``downstream'' tasks such as action localisation, which are smaller due to their finer-grained annotations. In this paper, we question this approach, and propose co-finetuning -- simultaneously training a single model on multiple ``upstream'' and ``downstream'' tasks. We demonstrate that co-finetuning outperforms traditional transfer learning when using the same total amount of data, and also show how we can easily extend our approach to multiple ``upstream'' datasets to further improve performance. In particular, co-finetuning significantly improves the performance on rare classes in our downstream task, as it has a regularising effect, and enables the network to learn feature representations that transfer between different datasets. Finally, we observe how co-finetuning with public, video classification datasets, we are able to achieve state-of-the-art results for spatio-temporal action localisation on the challenging AVA and AVA-Kinetics datasets, outperforming recent works which develop intricate models.

Chenxi Liu, Lixu Wang, Lingjuan Lyu et al.

In real-world applications, deep learning models often run in non-stationary environments where the target data distribution continually shifts over time. There have been numerous domain adaptation (DA) methods in both online and offline modes to improve cross-domain adaptation ability. However, these DA methods typically only provide good performance after a long period of adaptation, and perform poorly on new domains before and during adaptation - in what we call the "Unfamiliar Period", especially when domain shifts happen suddenly and significantly. On the other hand, domain generalization (DG) methods have been proposed to improve the model generalization ability on unadapted domains. However, existing DG works are ineffective for continually changing domains due to severe catastrophic forgetting of learned knowledge. To overcome these limitations of DA and DG in handling the Unfamiliar Period during continual domain shift, we propose RaTP, a framework that focuses on improving models' target domain generalization (TDG) capability, while also achieving effective target domain adaptation (TDA) capability right after training on certain domains and forgetting alleviation (FA) capability on past domains. RaTP includes a training-free data augmentation module to prepare data for TDG, a novel pseudo-labeling mechanism to provide reliable supervision for TDA, and a prototype contrastive alignment algorithm to align different domains for achieving TDG, TDA and FA. Extensive experiments on Digits, PACS, and DomainNet demonstrate that RaTP significantly outperforms state-of-the-art works from Continual DA, Source-Free DA, Test-Time/Online DA, Single DG, Multiple DG and Unified DA&DG in TDG, and achieves comparable TDA and FA capabilities.

Chen Sun, Calvin Luo, Xingyi Zhou et al.

We aim to investigate whether end-to-end learning of visual reasoning can be achieved with general-purpose neural networks, with the help of visual pretraining. A positive result would refute the common belief that explicit visual abstraction (e.g. object detection) is essential for compositional generalization on visual reasoning, and confirm the feasibility of a neural network "generalist" to solve visual recognition and reasoning tasks. We propose a simple and general self-supervised framework which "compresses" each video frame into a small set of tokens with a transformer network, and reconstructs the remaining frames based on the compressed temporal context. To minimize the reconstruction loss, the network must learn a compact representation for each image, as well as capture temporal dynamics and object permanence from temporal context. We perform evaluation on two visual reasoning benchmarks, CATER and ACRE. We observe that pretraining is essential to achieve compositional generalization for end-to-end visual reasoning. Our proposed framework outperforms traditional supervised pretraining, including image classification and explicit object detection, by large margins.

Qi Zhao, Haotian Fu, Chen Sun et al.

Long-horizon decision-making tasks present significant challenges for LLM-based agents due to the need for extensive planning over multiple steps. In this paper, we propose a hierarchical framework that decomposes complex tasks into manageable subgoals, utilizing separate LLMs for subgoal prediction and low-level action generation. To address the challenge of creating training signals for unannotated datasets, we develop a reward model that leverages multimodal environment feedback to automatically generate reward signals. We introduce Environment Preference Optimization (EPO), a novel method that generates preference signals from the environment's feedback and uses them to train LLM-based agents. Extensive experiments on ALFRED demonstrate the state-of-the-art performance of our framework, achieving first place on the ALFRED public leaderboard and showcasing its potential to improve long-horizon decision-making in diverse environments.

Chen Sun, Liang Gao, Xinyu Li et al.

Surface defect detection is one of the most essential processes for industrial quality inspection. Deep learning-based surface defect detection methods have shown great potential. However, the well-performed models usually require large training data and can only detect defects that appeared in the training stage. When facing incremental few-shot data, defect detection models inevitably suffer from catastrophic forgetting and misclassification problem. To solve these problems, this paper proposes a new knowledge distillation network, called Dual Knowledge Align Network (DKAN). The proposed DKAN method follows a pretraining-finetuning transfer learning paradigm and a knowledge distillation framework is designed for fine-tuning. Specifically, an Incremental RCNN is proposed to achieve decoupled stable feature representation of different categories. Under this framework, a Feature Knowledge Align (FKA) loss is designed between class-agnostic feature maps to deal with catastrophic forgetting problems, and a Logit Knowledge Align (LKA) loss is deployed between logit distributions to tackle misclassification problems. Experiments have been conducted on the incremental Few-shot NEU-DET dataset and results show that DKAN outperforms other methods on various few-shot scenes, up to 6.65% on the mean Average Precision metric, which proves the effectiveness of the proposed method.

Zilai Zeng, Ce Zhang, Shijie Wang et al.

Recent work has demonstrated the effectiveness of formulating decision making as supervised learning on offline-collected trajectories. Powerful sequence models, such as GPT or BERT, are often employed to encode the trajectories. However, the benefits of performing sequence modeling on trajectory data remain unclear. In this work, we investigate whether sequence modeling has the ability to condense trajectories into useful representations that enhance policy learning. We adopt a two-stage framework that first leverages sequence models to encode trajectory-level representations, and then learns a goal-conditioned policy employing the encoded representations as its input. This formulation allows us to consider many existing supervised offline RL methods as specific instances of our framework. Within this framework, we introduce Goal-Conditioned Predictive Coding (GCPC), a sequence modeling objective that yields powerful trajectory representations and leads to performant policies. Through extensive empirical evaluations on AntMaze, FrankaKitchen and Locomotion environments, we observe that sequence modeling can have a significant impact on challenging decision making tasks. Furthermore, we demonstrate that GCPC learns a goal-conditioned latent representation encoding the future trajectory, which enables competitive performance on all three benchmarks.

Yunkang Cao, Xiaohao Xu, Chen Sun et al.

This technical report introduces the winning solution of the team Segment Any Anomaly for the CVPR2023 Visual Anomaly and Novelty Detection (VAND) challenge. Going beyond uni-modal prompt, e.g., language prompt, we present a novel framework, i.e., Segment Any Anomaly + (SAA$+$), for zero-shot anomaly segmentation with multi-modal prompts for the regularization of cascaded modern foundation models. Inspired by the great zero-shot generalization ability of foundation models like Segment Anything, we first explore their assembly (SAA) to leverage diverse multi-modal prior knowledge for anomaly localization. Subsequently, we further introduce multimodal prompts (SAA$+$) derived from domain expert knowledge and target image context to enable the non-parameter adaptation of foundation models to anomaly segmentation. The proposed SAA$+$ model achieves state-of-the-art performance on several anomaly segmentation benchmarks, including VisA and MVTec-AD, in the zero-shot setting. We will release the code of our winning solution for the CVPR2023 VAN.

Tian Yun, Zilai Zeng, Kunal Handa et al.

Decision making via sequence modeling aims to mimic the success of language models, where actions taken by an embodied agent are modeled as tokens to predict. Despite their promising performance, it remains unclear if embodied sequence modeling leads to the emergence of internal representations that represent the environmental state information. A model that lacks abstract state representations would be liable to make decisions based on surface statistics which fail to generalize. We take the BabyAI environment, a grid world in which language-conditioned navigation tasks are performed, and build a sequence modeling Transformer, which takes a language instruction, a sequence of actions, and environmental observations as its inputs. In order to investigate the emergence of abstract state representations, we design a "blindfolded" navigation task, where only the initial environmental layout, the language instruction, and the action sequence to complete the task are available for training. Our probing results show that intermediate environmental layouts can be reasonably reconstructed from the internal activations of a trained model, and that language instructions play a role in the reconstruction accuracy. Our results suggest that many key features of state representations can emerge via embodied sequence modeling, supporting an optimistic outlook for applications of sequence modeling objectives to more complex embodied decision-making domains.

Kaleb Newman, Shijie Wang, Yuan Zang et al.

For a vision-language model (VLM) to understand the physical world, such as cause and effect, a first step is to capture the temporal dynamics of the visual world, for example how the physical states of objects evolve over time (e.g. a whole apple into a sliced apple). Our paper aims to investigate if VLMs pre-trained on web-scale data learn to encode object states, which can be extracted with zero-shot text prompts. We curate an object state recognition dataset ChangeIt-Frames, and evaluate nine open-source VLMs, including models trained with contrastive and generative objectives. We observe that while these state-of-the-art vision-language models can reliably perform object recognition, they consistently fail to accurately distinguish the objects' physical states. Through extensive experiments, we identify three areas for improvements for VLMs to better encode object states, namely the quality of object localization, the architecture to bind concepts to objects, and the objective to learn discriminative visual and language encoders on object states. Data and code are released.

Yu Zhao, Zhenzhou Jin, Jinke Tang et al.

With the widespread application of location-based services, fingerprint-based localization has demonstrated advantages in environments with complex signal propagation. Deep learning has significantly improved the efficiency of both offline training and online matching in localization processes. However, existing fingerprints only contain terminal position information without capturing motion states, and neural network designs have not fully incorporated structural features such as fingerprint sparsity. In this paper, we propose a triple-beam fingerprint (TBF) incorporating Doppler information and design a Transformer-based localization and orientation awareness network (LOA-Net) to simultaneously estimate user position and motion direction in massive multiple-input multiple-output (MIMO) orthogonal frequency division multiplexing (OFDM) systems. We first show the correlation between TBF and multipath information, and investigate the collinearity of different TBFs, demonstrating that TBF is an effective small-size sparse fingerprint. Then, we propose LOA-Net containing a mask-augmented detection Transformer for regression (MaskDETR-Reg) module and a fusion-enhanced Transformer for direction classification (Fusion-TDC) module to process angle-delay domain information and Doppler domain information, respectively. Finally, in the simulation of indoor scenarios defined in 3GPP 38.901, the proposed method achieves significantly better localization accuracy than weighted $K$-nearest neighbors (WKNN), 2D and 3D convolutional neural networks (CNNs), and achieves satisfactory motion direction estimation accuracy.

Apoorv Khandelwal, Ellie Pavlick, Chen Sun

Modular neural networks without additional training have recently been shown to surpass end-to-end neural networks on challenging vision-language tasks. The latest such methods simultaneously introduce LLM-based code generation to build programs and a number of skill-specific, task-oriented modules to execute them. In this paper, we focus on ViperGPT and ask where its additional performance comes from and how much is due to the (state-of-art, end-to-end) BLIP-2 model it subsumes vs. additional symbolic components. To do so, we conduct a controlled study (comparing end-to-end, modular, and prompting-based methods across several VQA benchmarks). We find that ViperGPT's reported gains over BLIP-2 can be attributed to its selection of task-specific modules, and when we run ViperGPT using a more task-agnostic selection of modules, these gains go away. Additionally, ViperGPT retains much of its performance if we make prominent alterations to its selection of modules: e.g. removing or retaining only BLIP-2. Finally, we compare ViperGPT against a prompting-based decomposition strategy and find that, on some benchmarks, modular approaches significantly benefit by representing subtasks with natural language, instead of code.

Qiang Tong, Jinrui Wang, Wenshuang Yang et al.

The utilization of AIoT technology has become a crucial trend in modern poultry management, offering the potential to optimize farming operations and reduce human workloads. This paper presents a real-time and compact edge-AI enabled detector designed to identify chickens and their healthy statuses using frames captured by a lightweight and intelligent camera equipped with an edge-AI enabled CMOS sensor. To ensure efficient deployment of the proposed compact detector within the memory-constrained edge-AI enabled CMOS sensor, we employ a FCOS-Lite detector leveraging MobileNet as the backbone. To mitigate the issue of reduced accuracy in compact edge-AI detectors without incurring additional inference costs, we propose a gradient weighting loss function as classification loss and introduce CIOU loss function as localization loss. Additionally, we propose a knowledge distillation scheme to transfer valuable information from a large teacher detector to the proposed FCOS-Lite detector, thereby enhancing its performance while preserving a compact model size. Experimental results demonstrate the proposed edge-AI enabled detector achieves commendable performance metrics, including a mean average precision (mAP) of 95.1$\%$ and an F1-score of 94.2$\%$, etc. Notably, the proposed detector can be efficiently deployed and operates at a speed exceeding 20 FPS on the edge-AI enabled CMOS sensor, achieved through int8 quantization. That meets practical demands for automated poultry health monitoring using lightweight intelligent cameras with low power consumption and minimal bandwidth costs.

Chen Sun, Shiyao Ma, Ce Zheng et al.

User selection has become crucial for decreasing the communication costs of federated learning (FL) over wireless networks. However, centralized user selection causes additional system complexity. This study proposes a network intrinsic approach of distributed user selection that leverages the radio resource competition mechanism in random access. Taking the carrier sensing multiple access (CSMA) mechanism as an example of random access, we manipulate the contention window (CW) size to prioritize certain users for obtaining radio resources in each round of training. Training data bias is used as a target scenario for FL with user selection. Prioritization is based on the distance between the newly trained local model and the global model of the previous round. To avoid excessive contribution by certain users, a counting mechanism is used to ensure fairness. Simulations with various datasets demonstrate that this method can rapidly achieve convergence similar to that of the centralized user selection approach.

Minghao Ning, Yufeng Yang, Keqi Shu et al.

Vehicle-infrastructure (V2I) cooperative perception can substantially extend the range, coverage, and robustness of autonomous driving systems beyond the limits of onboard-only sensing, particularly in occluded and adverse-weather environments. However, its practical value is still difficult to quantify because existing benchmarks do not adequately capture large-scale multi-node deployments, realistic communication conditions, and adverse-weather operation. This paper presents CoInfra, a deployable cooperative infrastructure perception platform comprising 14 roadside sensor nodes connected through a commercial 5G network, together with a large-scale dataset and an open-source system stack for V2I cooperation research. The system supports synchronized multi-node sensing and delay-aware fusion under real 5G communication constraints. The released dataset covers an eight-node urban roundabout under four weather conditions (sunny, rainy, heavy snow, and freezing rain) and contains 294k LiDAR frames, 589k camera images, and 332k globally consistent 3D bounding boxes. It also includes a synchronized V2I subset collected with an autonomous vehicle. Beyond standard perception benchmarks, we further evaluate whether infrastructure sensing improves awareness of safety-critical traffic participants during roundabout interactions. In structured conflict scenarios, V2I cooperation increases critical-frame completeness from 33%-46% with vehicle-only sensing to 86%-100%. These results show that multi-node infrastructure perception can significantly improve situational awareness in conflict-rich traffic scenarios where vehicle-only sensing is most limited.

Yunkang Cao, Xiaohao Xu, Chen Sun et al.

Anomaly detection is a crucial task across different domains and data types. However, existing anomaly detection models are often designed for specific domains and modalities. This study explores the use of GPT-4V(ision), a powerful visual-linguistic model, to address anomaly detection tasks in a generic manner. We investigate the application of GPT-4V in multi-modality, multi-domain anomaly detection tasks, including image, video, point cloud, and time series data, across multiple application areas, such as industrial, medical, logical, video, 3D anomaly detection, and localization tasks. To enhance GPT-4V's performance, we incorporate different kinds of additional cues such as class information, human expertise, and reference images as prompts.Based on our experiments, GPT-4V proves to be highly effective in detecting and explaining global and fine-grained semantic patterns in zero/one-shot anomaly detection. This enables accurate differentiation between normal and abnormal instances. Although we conducted extensive evaluations in this study, there is still room for future evaluation to further exploit GPT-4V's generic anomaly detection capacity from different aspects. These include exploring quantitative metrics, expanding evaluation benchmarks, incorporating multi-round interactions, and incorporating human feedback loops. Nevertheless, GPT-4V exhibits promising performance in generic anomaly detection and understanding, thus opening up a new avenue for anomaly detection.

Kang Yang, Peng Wang, Lantao Li et al.

Multi-modal collaborative perception calls for great attention to enhancing the safety of autonomous driving. However, current multi-modal approaches remain a ``local fusion to communication'' sequence, which fuses multi-modal data locally and needs high bandwidth to transmit an individual's feature data before collaborative fusion. EIMC innovatively proposes an early collaborative paradigm. It injects lightweight collaborative voxels, transmitted by neighbor agents, into the ego's local modality-fusion step, yielding compact yet informative 3D collaborative priors that tighten cross-modal alignment. Next, a heatmap-driven consensus protocol identifies exactly where cooperation is needed by computing per-pixel confidence heatmaps. Only the Top-K instance vectors located in these low-confidence, high-discrepancy regions are queried from peers, then fused via cross-attention for completion. Afterwards, we apply a refinement fusion that involves collecting the top-K most confident instances from each agent and enhancing their features using self-attention. The above instance-centric messaging reduces redundancy while guaranteeing that critical occluded objects are recovered. Evaluated on OPV2V and DAIR-V2X, EIMC attains 73.01\% AP@0.5 while reducing byte bandwidth usage by 87.98\% compared with the best published multi-modal collaborative detector. Code publicly released at https://github.com/sidiangongyuan/EIMC.

Dylan Ebert, Chen Sun, Ellie Pavlick

Distributional models learn representations of words from text, but are criticized for their lack of grounding, or the linking of text to the non-linguistic world. Grounded language models have had success in learning to connect concrete categories like nouns and adjectives to the world via images and videos, but can struggle to isolate the meaning of the verbs themselves from the context in which they typically occur. In this paper, we investigate the extent to which trajectories (i.e. the position and rotation of objects over time) naturally encode verb semantics. We build a procedurally generated agent-object-interaction dataset, obtain human annotations for the verbs that occur in this data, and compare several methods for representation learning given the trajectories. We find that trajectories correlate as-is with some verbs (e.g., fall), and that additional abstraction via self-supervised pretraining can further capture nuanced differences in verb meaning (e.g., roll vs. slide).

Shijie Wang, Dahun Kim, Ali Taalimi et al.

Visual grounding tasks aim to localize image regions based on natural language references. In this work, we explore whether generative VLMs predominantly trained on image-text data could be leveraged to scale up the text annotation of visual grounding data. We find that grounding knowledge already exists in generative VLM and can be elicited by proper prompting. We thus prompt a VLM to generate object-level descriptions by feeding it object regions from existing object detection datasets. We further propose attribute modeling to explicitly capture the important object attributes, and spatial relation modeling to capture inter-object relationship, both of which are common linguistic pattern in referring expression. Our constructed dataset (500K images, 1M objects, 16M referring expressions) is one of the largest grounding datasets to date, and the first grounding dataset with purely model-generated queries and human-annotated objects. To verify the quality of this data, we conduct zero-shot transfer experiments to the popular RefCOCO benchmarks for both referring expression comprehension (REC) and segmentation (RES) tasks. On both tasks, our model significantly outperform the state-of-the-art approaches without using human annotated visual grounding data. Our results demonstrate the promise of generative VLM to scale up visual grounding in the real world. Code and models will be released.

Dylan Ebert, Chen Sun, Ellie Pavlick

Three-dimensional trajectories, or the 3D position and rotation of objects over time, have been shown to encode key aspects of verb semantics (e.g., the meanings of roll vs. slide). However, most multimodal models in NLP use 2D images as representations of the world. Given the importance of 3D space in formal models of verb semantics, we expect that these 2D images would result in impoverished representations that fail to capture nuanced differences in meaning. This paper tests this hypothesis directly in controlled experiments. We train self-supervised image and trajectory encoders, and then evaluate them on the extent to which each learns to differentiate verb concepts. Contrary to our initial expectations, we find that 2D visual modalities perform similarly well to 3D trajectories. While further work should be conducted on this question, our initial findings challenge the conventional wisdom that richer environment representations necessarily translate into better representation learning for language.

Shijie Wang, Qi Zhao, Minh Quan Do et al.

What makes good representations for video understanding, such as anticipating future activities, or answering video-conditioned questions? While earlier approaches focus on end-to-end learning directly from video pixels, we propose to revisit text-based representations, such as general-purpose video captions, which are interpretable and can be directly consumed by large language models (LLMs). Intuitively, different video understanding tasks may require representations that are complementary and at different granularity. To this end, we propose versatile action models (Vamos), a learning framework powered by a large language model as the ``reasoner'', and can flexibly leverage visual embedding and free-form text descriptions as its input. To interpret the important text evidence for question answering, we generalize the concept bottleneck model to work with tokens and nonlinear models, which uses hard attention to select a small subset of tokens from the free-form text as inputs to the LLM reasoner. We evaluate Vamos on five complementary benchmarks, Ego4D, NeXT-QA, IntentQA, Spacewalk-18, and EgoSchema, on its capability to model temporal dynamics, encode visual history, and perform reasoning. Surprisingly, we observe that text-based representations consistently achieve competitive performance on all benchmarks, and that visual embeddings provide marginal or no performance improvement, demonstrating the effectiveness of text-based video representation in the LLM era. We also demonstrate that our token bottleneck model is able to select relevant evidence from free-form text, support test-time intervention, and achieves nearly 5 times inference speedup while keeping a competitive question answering performance. Code and models are publicly released at https://brown-palm.github.io/Vamos/

Ce Zhang, Changcheng Fu, Shijie Wang et al.

This paper focuses on building object-centric representations for long-term action anticipation in videos. Our key motivation is that objects provide important cues to recognize and predict human-object interactions, especially when the predictions are longer term, as an observed "background" object could be used by the human actor in the future. We observe that existing object-based video recognition frameworks either assume the existence of in-domain supervised object detectors or follow a fully weakly-supervised pipeline to infer object locations from action labels. We propose to build object-centric video representations by leveraging visual-language pretrained models. This is achieved by "object prompts", an approach to extract task-specific object-centric representations from general-purpose pretrained models without finetuning. To recognize and predict human-object interactions, we use a Transformer-based neural architecture which allows the "retrieval" of relevant objects for action anticipation at various time scales. We conduct extensive evaluations on the Ego4D, 50Salads, and EGTEA Gaze+ benchmarks. Both quantitative and qualitative results confirm the effectiveness of our proposed method.

Zehua Zhao, Zhixian Huang, Junren Li et al.

Current benchmarks for evaluating the chemical reasoning capabilities of Large Language Models (LLMs) are limited by oversimplified tasks, lack of process-level evaluation, and misalignment with expert-level chemistry skills. To address these issues, we introduce SUPERChem, a benchmark of 500 expert-curated reasoning-intensive chemistry problems, covering diverse subfields and provided in both multimodal and text-only formats. Original content and an iterative curation pipeline eliminate flawed items and mitigate data contamination. Each problem is paired with an expert-authored solution path, enabling Reasoning Path Fidelity (RPF) scoring to evaluate reasoning quality beyond final-answer accuracy. Evaluations against a human baseline of 40.3% accuracy show that even the best-performing model, GPT-5 (High), reaches only 38.5%, followed closely by Gemini 2.5 Pro (37.9%) and DeepSeek-V3.1-Think (37.3%). SUPERChem elicits multi-step, multimodal reasoning, reveals model-dependent effects of visual information, and distinguishes high-fidelity reasoners from heuristic ones. By providing a challenging benchmark and a reliable evaluation framework, SUPERChem aims to facilitate the advancement of LLMs toward expert-level chemical intelligence. The dataset of the benchmark is available at https://huggingface.co/datasets/ZehuaZhao/SUPERChem.

Junyi Zhang, Charles Herrmann, Junhwa Hur et al.

Feedforward geometric foundation models achieve strong short-window reconstruction, yet scaling them to minutes-long videos is bottlenecked by quadratic attention complexity or limited effective memory in recurrent designs. We present LoGeR (Long-context Geometric Reconstruction), a novel architecture that scales dense 3D reconstruction to extremely long sequences without post-optimization. LoGeR processes video streams in chunks, leveraging strong bidirectional priors for high-fidelity intra-chunk reasoning. To manage the critical challenge of coherence across chunk boundaries, we propose a learning-based hybrid memory module. This dual-component system combines a parametric Test-Time Training (TTT) memory to anchor the global coordinate frame and prevent scale drift, alongside a non-parametric Sliding Window Attention (SWA) mechanism to preserve uncompressed context for high-precision adjacent alignment. Remarkably, this memory architecture enables LoGeR to be trained on sequences of 128 frames, and generalize up to thousands of frames during inference. Evaluated across standard benchmarks and a newly repurposed VBR dataset with sequences of up to 19k frames, LoGeR substantially outperforms prior state-of-the-art feedforward methods--reducing ATE on KITTI by over 74%--and achieves robust, globally consistent reconstruction over unprecedented horizons.

Lantao Li, Chen Sun

Multi-agent multi-lidar sensor fusion between connected vehicles for cooperative perception has recently been recognized as the best technique for minimizing the blind zone of individual vehicular perception systems and further enhancing the overall safety of autonomous driving systems. This technique relies heavily on the reliability and availability of vehicle-to-everything (V2X) communication. In practical sensor fusion application scenarios, the non-line-of-sight (NLOS) issue causes blind zones for not only the perception system but also V2X direct communication. To counteract underlying communication issues, we introduce an abstract perception matrix matching method for quick sensor fusion matching procedures and mobility-height hybrid relay determination procedures, proactively improving the efficiency and performance of V2X communication to serve the upper layer application fusion requirements. To demonstrate the effectiveness of our solution, we design a new simulation framework to consider autonomous driving, sensor fusion and V2X communication in general, paving the way for end-to-end performance evaluation and further solution derivation.

Nate Gillman, Yinghua Zhou, Zitian Tang et al.

Recent advancements in video generation have enabled the development of ``world models'' capable of simulating potential futures for robotics and planning. However, specifying precise goals for these models remains a challenge; text instructions are often too abstract to capture physical nuances, while target images are frequently infeasible to specify for dynamic tasks. To address this, we introduce Goal Force, a novel framework that allows users to define goals via explicit force vectors and intermediate dynamics, mirroring how humans conceptualize physical tasks. We train a video generation model on a curated dataset of synthetic causal primitives-such as elastic collisions and falling dominos-teaching it to propagate forces through time and space. Despite being trained on simple physics data, our model exhibits remarkable zero-shot generalization to complex, real-world scenarios, including tool manipulation and multi-object causal chains. Our results suggest that by grounding video generation in fundamental physical interactions, models can emerge as implicit neural physics simulators, enabling precise, physics-aware planning without reliance on external engines. We release all datasets, code, model weights, and interactive video demos at our project page.

Wei Zhang, Ping Gong, Yujie Wang et al.

Object Goal Navigation (ObjectNav) in temporally changing indoor environments is challenging because object relocation can invalidate historical scene knowledge. To address this issue, we propose a probabilistic planning framework that combines uncertainty-aware scene priors with online target relevance estimates derived from a Vision Language Model (VLM). The framework contains a dual-layer semantic mapping module and a real-time planner. The mapping module includes an Information Gain Map (IGM) built from a 3D scene graph (3DSG) during prior exploration to model object co-occurrence relations and provide global guidance on likely target regions. It also maintains a VLM score map (VLM-SM) that fuses confidence-weighted semantic observations into the map for local validation of the current scene. Based on these two cues, we develop a planner that jointly exploits information gain and semantic evidence for online decision making. The planner biases tree expansion toward semantically salient regions with high prior likelihood and strong online relevance (IGV-RRT), while preserving kinematic feasibility through gradient-based analysis. Simulation and real-world experiments demonstrate that the proposed method effectively mitigates the impact of object rearrangement, achieving higher search efficiency and success rates than representative baselines in complex indoor environments.

Bosun Liang, Shuo Pei, Zirui Chen et al.

Reinforcement learning often produces high-frequency oscillatory control signals that undermine the safety and stability required for physical deployment. Explicit action chunking addresses this by predicting fixed-horizon trajectories but scales the policy output dimension proportionally with the horizon length, leading to optimization difficulties and incompatibility with standard step-wise interaction. To overcome these challenges, this paper proposes Dual-Window Smoothing (DWS), an implicit action chunking framework for smooth continuous control. Unlike explicit methods, DWS enforces temporal coherence without expanding the action space. It uses a dual-window design: an execution window that ensures physical smoothness through deterministic modulation, and a value window that aligns temporal-difference targets over the horizon to correct critic bias caused by open-loop execution. DWS also includes a lightweight actor-side temporal regularizer based on first-order action differences to promote global continuity. This design effectively bridges the gap between temporal abstraction and reactive step-wise control. Experiments on benchmarks including the DeepMind Control Suite and industrial energy management tasks show that DWS outperforms state-of-the-art (SOTA) baselines. In complex vision-based autonomous driving tasks, DWS achieves smoother control, safer behavior with reduced jitter, and attains a 100% success rate.

Chen Sun, Yash Vekaria, Rishab Nithyanand

As LLM-driven agents begin to autonomously navigate the web, their ability to interpret and respond to manipulative interface design becomes critical. A fundamental question that emerges is: can such agents reliably recognize patterns of friction, misdirection, and coercion in interface design (i.e., dark patterns)? We study this question in a setting where the workflows are consequential: website portals associated with the submission of CCPA-related data rights requests. These portals operationalize statutory rights, but they are implemented as interactive interfaces whose design can be structured to facilitate, burden, or subtly discourage the exercise of those rights. We design and deploy an LLM-driven auditing agent capable of end-to-end traversal of rights-request workflows, structured evidence gathering, and classification of potential dark patterns. Across a set of 456 data broker websites, we evaluate: (1) the ability of the agent to consistently locate and complete request flows, (2) the reliability and reproducibility of its dark pattern classifications, and (3) the conditions under which it fails or produces poor judgments. Our findings characterize both the feasibility and the limitations of using LLM-driven agents for scalable dark pattern auditing.

Chen Sun, Yash Vekaria, Zubair Shafiq et al.

YouTube has evolved into a powerful platform that where creators monetize their influence through affiliate marketing, raising concerns about transparency and ethics, especially when creators fail to disclose their affiliate relationships. Although regulatory agencies like the US Federal Trade Commission (FTC) have issued guidelines to address these issues, non-compliance and consumer harm persist, and the extent of these problems remains unclear. In this paper, we introduce tools, developed with insights from recent advances in Web measurement and NLP research, to examine the state of the affiliate marketing ecosystem on YouTube. We apply these tools to a 10-year dataset of 2 million videos from nearly 540,000 creators, analyzing the prevalence of affiliate marketing on YouTube and the rates of non-compliant behavior. Our findings reveal that affiliate links are widespread, yet dis- closure compliance remains low, with most videos failing to meet FTC standards. Furthermore, we analyze the effects of different stakeholders in improving disclosure behavior. Our study suggests that the platform is highly associated with improved compliance through standardized disclosure features. We recommend that regulators and affiliate partners collaborate with platforms to enhance transparency, accountability, and trust in the influencer economy.

Chen Sun, Beilin Xu, Boheng Tan et al.

In industrial commodity recommendation systems, the representation quality of Item-Id vocabularies directly impacts the scalability and generalization ability of recommendation models. A key challenge is that traditional Item-Id vocabularies, when subjected to sparse scaling, suffer from low-frequency information interference, which restricts their expressive power for massive item sets and leads to representation collapse. To address this issue, we propose an Orthogonal Constrained Projection method to optimize embedding representation. By enforcing orthogonality, the projection constrains the backpropagation manifold, aligning the singular value spectrum of the learned embeddings with the orthogonal basis. This alignment ensures high singular entropy, thereby preserving isotropic generalized features while suppressing spurious correlations and overfitting to rare items. Empirical results demonstrate that OCP accelerates loss convergence and enhances the model's scalability; notably, it enables consistent performance gains when scaling up dense layers. Large-scale industrial deployment on JD.com further confirms its efficacy, yielding a 12.97% increase in UCXR and an 8.9% uplift in GMV, highlighting its robust utility for scaling up both sparse vocabularies and dense architectures.

Hui Zeng, Jingyuan Xue, Meng Hao et al.

This paper unveils CG-Eval, the first-ever comprehensive and automated evaluation framework designed for assessing the generative capabilities of large Chinese language models across a spectrum of academic disciplines. CG-Eval stands out for its automated process, which critically assesses models based on their proficiency in generating precise and contextually relevant responses to a diverse array of questions within six key domains: Science and Engineering, Humanities and Social Sciences, Mathematical Calculations, Medical Practitioner Qualification Examination, Judicial Examination, and Certified Public Accountant Examination. Alongside this, we introduce Gscore, an innovative composite index developed from a weighted sum of multiple metrics. Gscore uniquely automates the quality measurement of a model's text generation against reference standards, providing a detailed and nuanced assessment of model performance. This automation not only enhances the efficiency and scalability of the evaluation process but also ensures objective and consistent assessment across various models. The detailed test data and results, highlighting the robust capabilities and comparative performance of the evaluated models, are accessible at http://cgeval.besteasy.com/.

Yiming Shu, Pei Liu, Tiange Zhang et al.

Sustaining long-term interactions remains a bottleneck for Large Language Models (LLMs), as their limited context windows struggle to manage dialogue histories that extend over time. Existing memory systems often treat interactions as disjointed snippets, failing to capture the underlying narrative coherence of the dialogue stream. We propose TraceMem, a cognitively-inspired framework that weaves structured, narrative memory schemata from user conversational traces through a three-stage pipeline: (1) Short-term Memory Processing, which employs a deductive topic segmentation approach to demarcate episode boundaries and extract semantic representation; (2) Synaptic Memory Consolidation, a process that summarizes episodes into episodic memories before distilling them alongside semantics into user-specific traces; and (3) Systems Memory Consolidation, which utilizes two-stage hierarchical clustering to organize these traces into coherent, time-evolving narrative threads under unifying themes. These threads are encapsulated into structured user memory cards, forming narrative memory schemata. For memory utilization, we provide an agentic search mechanism to enhance reasoning process. Evaluation on the LoCoMo benchmark shows that TraceMem achieves state-of-the-art performance with a brain-inspired architecture. Analysis shows that by constructing coherent narratives, it surpasses baselines in multi-hop and temporal reasoning, underscoring its essential role in deep narrative comprehension. Additionally, we provide an open discussion on memory systems, offering our perspectives and future outlook on the field. Our code implementation is available at: https://github.com/YimingShu-teay/TraceMem

Calvin Luo, Mandy He, Zilai Zeng et al.

Training an agent to achieve particular goals or perform desired behaviors is often accomplished through reinforcement learning, especially in the absence of expert demonstrations. However, supporting novel goals or behaviors through reinforcement learning requires the ad-hoc design of appropriate reward functions, which quickly becomes intractable. To address this challenge, we propose Text-Aware Diffusion for Policy Learning (TADPoLe), which uses a pretrained, frozen text-conditioned diffusion model to compute dense zero-shot reward signals for text-aligned policy learning. We hypothesize that large-scale pretrained generative models encode rich priors that can supervise a policy to behave not only in a text-aligned manner, but also in alignment with a notion of naturalness summarized from internet-scale training data. In our experiments, we demonstrate that TADPoLe is able to learn policies for novel goal-achievement and continuous locomotion behaviors specified by natural language, in both Humanoid and Dog environments. The behaviors are learned zero-shot without ground-truth rewards or expert demonstrations, and are qualitatively more natural according to human evaluation. We further show that TADPoLe performs competitively when applied to robotic manipulation tasks in the Meta-World environment, without having access to any in-domain demonstrations.

Chiheng Lou, Sheng Qi, Rui Kang et al.

Deploying multiple models within shared GPU clusters is promising for improving resource efficiency in large language model (LLM) serving. Existing multi-LLM serving systems optimize GPU utilization at the cost of worse inference performance, especially time-to-first-token (TTFT). We identify the root cause of such compromise as their unawareness of future workload characteristics. In contrast, recent analysis on real-world traces has shown the high periodicity and long-term predictability of LLM serving workloads. We propose universal GPU workers to enable one-for-many GPU prewarming that loads models with knowledge of future workloads. Based on universal GPU workers, we design and build WarmServe, a multi-LLM serving system that (1) mitigates cluster-wide prewarming interference by adopting an evict-aware model placement strategy, (2) prepares universal GPU workers in advance by proactive prewarming, and (3) manages GPU memory with a zero-overhead memory switching mechanism. Evaluation under real-world datasets shows that WarmServe improves TTFT by up to 50.8$\times$ compared to the state-of-the-art autoscaling-based system, while being capable of serving up to 2.5$\times$ more requests compared to the GPU-sharing system.

Apoorv Khandelwal, Tian Yun, Nihal V. Nayak et al.

Pre-training is notoriously compute-intensive and academic researchers are notoriously under-resourced. It is, therefore, commonly assumed that academics can't pre-train models. In this paper, we seek to clarify this assumption. We first survey academic researchers to learn about their available compute and then empirically measure the time to replicate models on such resources. We introduce a benchmark to measure the time to pre-train models on given GPUs and also identify ideal settings for maximizing training speed. We run our benchmark on a range of models and academic GPUs, spending 2,000 GPU-hours on our experiments. Our results reveal a brighter picture for academic pre-training: for example, although Pythia-1B was originally trained on 64 GPUs for 3 days, we find it is also possible to replicate this model (with the same hyper-parameters) in 3x fewer GPU-days: i.e. on 4 GPUs in 18 days. We conclude with a cost-benefit analysis to help clarify the trade-offs between price and pre-training time. We believe our benchmark will help academic researchers conduct experiments that require training larger models on more data. We fully release our codebase at: https://github.com/apoorvkh/academic-pretraining.