Amit Singh

Kunal Dahiya, Nilesh Gupta, Deepak Saini et al.

Extreme Classification (XC) seeks to tag data points with the most relevant subset of labels from an extremely large label set. Performing deep XC with dense, learnt representations for data points and labels has attracted much attention due to its superiority over earlier XC methods that used sparse, hand-crafted features. Negative mining techniques have emerged as a critical component of all deep XC methods that allow them to scale to millions of labels. However, despite recent advances, training deep XC models with large encoder architectures such as transformers remains challenging. This paper identifies that memory overheads of popular negative mining techniques often force mini-batch sizes to remain small and slow training down. In response, this paper introduces NGAME, a light-weight mini-batch creation technique that offers provably accurate in-batch negative samples. This allows training with larger mini-batches offering significantly faster convergence and higher accuracies than existing negative sampling techniques. NGAME was found to be up to 16% more accurate than state-of-the-art methods on a wide array of benchmark datasets for extreme classification, as well as 3% more accurate at retrieving search engine queries in response to a user webpage visit to show personalized ads. In live A/B tests on a popular search engine, NGAME yielded up to 23% gains in click-through-rates.

Hendrik Buschmeier, Heike M. Buhl, Friederike Kern et al.

Explainability has become an important topic in computer science and artificial intelligence, leading to a subfield called Explainable Artificial Intelligence (XAI). The goal of providing or seeking explanations is to achieve (better) 'understanding' on the part of the explainee. However, what it means to 'understand' is still not clearly defined, and the concept itself is rarely the subject of scientific investigation. This conceptual article aims to present a model of forms of understanding for XAI-explanations and beyond. From an interdisciplinary perspective bringing together computer science, linguistics, sociology, philosophy and psychology, a definition of understanding and its forms, assessment, and dynamics during the process of giving everyday explanations are explored. Two types of understanding are considered as possible outcomes of explanations, namely enabledness, 'knowing how' to do or decide something, and comprehension, 'knowing that' -- both in different degrees (from shallow to deep). Explanations regularly start with shallow understanding in a specific domain and can lead to deep comprehension and enabledness of the explanandum, which we see as a prerequisite for human users to gain agency. In this process, the increase of comprehension and enabledness are highly interdependent. Against the background of this systematization, special challenges of understanding in XAI are discussed.

Nikhil J. Dhinagar, Amit Singh, Saket Ozarkar et al.

Transfer learning represents a recent paradigm shift in the way we build artificial intelligence (AI) systems. In contrast to training task-specific models, transfer learning involves pre-training deep learning models on a large corpus of data and minimally fine-tuning them for adaptation to specific tasks. Even so, for 3D medical imaging tasks, we do not know if it is best to pre-train models on natural images, medical images, or even synthetically generated MRI scans or video data. To evaluate these alternatives, here we benchmarked vision transformers (ViTs) and convolutional neural networks (CNNs), initialized with varied upstream pre-training approaches. These methods were then adapted to three unique downstream neuroimaging tasks with a range of difficulty: Alzheimer's disease (AD) and Parkinson's disease (PD) classification, "brain age" prediction. Experimental tests led to the following key observations: 1. Pre-training improved performance across all tasks including a boost of 7.4% for AD classification and 4.6% for PD classification for the ViT and 19.1% for PD classification and reduction in brain age prediction error by 1.26 years for CNNs, 2. Pre-training on large-scale video or synthetic MRI data boosted performance of ViTs, 3. CNNs were robust in limited-data settings, and in-domain pretraining enhanced their performances, 4. Pre-training improved generalization to out-of-distribution datasets and sites. Overall, we benchmarked different vision architectures, revealing the value of pre-training them with emerging datasets for model initialization. The resulting pre-trained models can be adapted to a range of downstream neuroimaging tasks, even when training data for the target task is limited.

Amit Singh, Vedant Nipane, Pulkit Agrawal et al.

Large language models (LLMs) demonstrate strong code generation abilities in general-purpose programming languages but remain limited in specialized domains such as low-level embedded systems programming. This domain involves hardware register manipulation, vendor-specific SDKs, real-time operating system APIs, and hardware abstraction layers that are underrepresented in standard pretraining corpora. We introduce H2LooP Spark Preview, a continual pretraining (CPT) pipeline that adapts the OLMo-3-7B-a fully open language model to the embedded systems domain using BF16 LoRA with rank-stabilized scaling on 8 NVIDIA H100 GPUs. Our training corpus is constructed from repository-datasheet pairs covering 100B tokens of raw embedded systems data across 117 manufacturers, processed using the hierarchical datasheet-to-code mapping approach proposed in SpecMap (Nipane et al., 2026). The resulting curated dataset split contains 23.5B tokens across 13 embedded domains. Continual pretraining with high-rank LoRA (r=512) yields substantial gains, reducing in-domain perplexity by 70.4% and held-out repository perplexity by 66.1%. On generative code completion benchmarks spanning 13 embedded domains, our 7B model outperforms Claude Opus 4.6 and Qwen3-Coder-30B on 8 categories in token accuracy, showing that targeted continual pretraining enables smaller open-weight models to rival frontier systems on specialized technical tasks. We release the production training checkpoint on Huggingface as an open-source artifact.

Jatin Kishnani, Mayank Goel, Amit Singh et al.

We present the first end-to-end demonstration of fine-tuning and serving Google's Gemma 4 31B model on TPU hardware, providing an empirical comparison of TPU and GPU platforms for large language model adaptation. Using LoRA on a Google TPU v5p-8 for training and TPU v6e-8 (Trillium) for inference, we document the full set of code-level adaptations required to port a GPU-native training recipe, built on PyTorch, HuggingFace TRL, and FSDP, to the JAX + Tunix/Qwix stack. These adaptations span mesh configuration, LoRA module naming conventions, sharding annotation corrections, gradient checkpointing, data pipeline restructuring, and a custom Orbax-to-safetensors checkpoint merging procedure. For inference, we detail the vLLM-TPU Docker setup necessary to serve Gemma 4 on v6e-8 and characterize the resulting latency and throughput profile. Compared with a 2xH100 GPU baseline under identical hyperparameters, TPU training completes 1.61x faster at 2.12x lower cost. Inference throughput is within 3% across platforms, while TPU achieves 2x lower time-to-first-token (235 ms vs. 475 ms). Together, the TPU configuration is 1.82x cheaper for a representative train-plus-service workload. Our work removes a critical gap in the open tooling ecosystem and provides practitioners with a reproducible, production-ready recipe for Gemma 4 deployment on TPU infrastructure.

Vedant Nipane, Pulkit Agrawal, Amit Singh

Establishing precise traceability between embedded systems datasheets and their corresponding code implementations remains a fundamental challenge in systems engineering, particularly for low-level software where manual mapping between specification documents and large code repositories is infeasible. Existing Traceability Link Recovery approaches primarily rely on lexical similarity and information retrieval techniques, which struggle to capture the semantic, structural, and symbol level relationships prevalent in embedded systems software. We present a hierarchical datasheet-to-code mapping methodology that employs large language models for semantic analysis while explicitly structuring the traceability process across multiple abstraction levels. Rather than performing direct specification-to-code matching, the proposed approach progressively narrows the search space through repository-level structure inference, file-level relevance estimation, and fine-grained symbollevel alignment. The method extends beyond function-centric mapping by explicitly covering macros, structs, constants, configuration parameters, and register definitions commonly found in systems-level C/C++ codebases. We evaluate the approach on multiple open-source embedded systems repositories using manually curated datasheet-to-code ground truth. Experimental results show substantial improvements over traditional information-retrieval-based baselines, achieving up to 73.3% file mapping accuracy. We significantly reduce computational overhead, lowering total LLM token consumption by 84% and end-to-end runtime by approximately 80%. This methodology supports automated analysis of large embedded software systems and enables downstream applications such as training data generation for systems-aware machine learning models, standards compliance verification, and large-scale specification coverage analysis.

Vipul Gupta, Shikhar Mohan, Lakshya Kumar et al.

In the competitive landscape of sponsored search, balancing retrieval quality with production latency is a critical challenge. While large retrieval models based on Small Language Models (SLMs) such as Qwen3-Embedding-4B/8B set strong upper bounds on public benchmarks, their deployment in high-throughput, latency-sensitive environments remains impractical. In this paper, we present HARNESS-LM (HLM), a three-phase training framework for transferring the capabilities of large-scale retrievers into compact, cost-efficient models. The approach comprises: (1) training a high-performance reference ("teacher") retriever by fine-tuning a billion-parameter-scale SLM; (2) aligning query representations via an L2 objective to distill knowledge into a sub-600M parameter student encoder; and (3) applying a final contrastive refinement stage to optimize the student for retrieval performance. We also present a comprehensive empirical study of key design choices, including alignment objectives, embedding dimensionality, model scale, architecture, and optimization strategies, to identify configurations that are most effective in production settings. On a real-world Bing Ads evaluation benchmark, HLM recovers over 98% of the reference retriever's precision across multiple settings, while delivering up to 27x lower online query-encoder latency and 20x higher throughput on NVIDIA A100 GPUs. Online A/B testing on Bing Ads further shows a +1% Revenue, +0.6% Impression, and +0.4% Click uplift over the current ensemble of retrievers running in production with the deployed 190M parameter model, clearly highlighting the practical efficacy of the HLM recipe in a real-world sponsored search setting.

Akash Kumar Mohankumar, Bhargav Dodla, Gururaj K et al.

Sponsored search is a key revenue source for search engines, where advertisers bid on keywords to target users or search queries of interest. However, finding relevant keywords for a given query is challenging due to the large and dynamic keyword space, ambiguous user/advertiser intents, and diverse possible topics and languages. In this work, we present a comprehensive comparison between two paradigms for online query rewriting: Generative (NLG) and Dense Retrieval (DR) methods. We observe that both methods offer complementary benefits that are additive. As a result, we show that around 40% of the high-quality keywords retrieved by the two approaches are unique and not retrieved by the other. To leverage the strengths of both methods, we propose CLOVER-Unity, a novel approach that unifies generative and dense retrieval methods in one single model. Through offline experiments, we show that the NLG and DR components of CLOVER-Unity consistently outperform individually trained NLG and DR models on public and internal benchmarks. Furthermore, we show that CLOVER-Unity achieves 9.8% higher good keyword density than the ensemble of two separate DR and NLG models while reducing computational costs by almost half. We conduct extensive online A/B experiments on Microsoft Bing in 140+ countries and achieve improved user engagement, with an average increase in total clicks by 0.89% and increased revenue by 1.27%. We also share our practical lessons and optimization tricks for deploying such unified models in production.

Akash Kumar Mohankumar, Gururaj K, Gagan Madan et al.

Accurately retrieving relevant bid keywords for user queries is critical in Sponsored Search but remains challenging, particularly for short, ambiguous queries. Existing dense and generative retrieval models often fail to capture nuanced user intent in these cases. To address this, we propose an approach to enhance query understanding by augmenting queries with rich contextual signals derived from web search results and large language models, stored in an online cache. Specifically, we use web search titles and snippets to ground queries in real-world information and utilize GPT-4 to generate query rewrites and explanations that clarify user intent. These signals are efficiently integrated through a Fusion-in-Decoder based Unity architecture, enabling both dense and generative retrieval with serving costs on par with traditional context-free models. To address scenarios where context is unavailable in the cache, we introduce context glancing, a curriculum learning strategy that improves model robustness and performance even without contextual signals during inference. Extensive offline experiments demonstrate that our context-aware approach substantially outperforms context-free models. Furthermore, online A/B testing on a prominent search engine across 160+ countries shows significant improvements in user engagement and revenue.

Siddhant Kharbanda, Devaansh Gupta, Gururaj K et al. · microsoft-research

Extreme Multi-label Classification (XMC) involves predicting a subset of relevant labels from an extremely large label space, given an input query and labels with textual features. Models developed for this problem have conventionally made use of dual encoder (DE) to embed the queries and label texts and one-vs-all (OvA) classifiers to rerank the shortlisted labels by the DE. While such methods have shown empirical success, a major drawback is their computational cost, often requiring upto 16 GPUs to train on the largest public dataset. Such a high cost is a consequence of calculating the loss over the entire label space. While shortlisting strategies have been proposed for classifiers, we aim to study such methods for the DE framework. In this work, we develop UniDEC, a loss-independent, end-to-end trainable framework which trains the DE and classifier together in a unified manner with a multi-class loss, while reducing the computational cost by 4-16x. This is done via the proposed pick-some-label (PSL) reduction, which aims to compute the loss on only a subset of positive and negative labels. These labels are carefully chosen in-batch so as to maximise their supervisory signals. Not only does the proposed framework achieve state-of-the-art results on datasets with labels in the order of millions, it is also computationally and resource efficient in achieving this performance on a single GPU. Code is made available at https://github.com/the-catalyst/UniDEC.

Amit Singh

In recent years, end to end steering prediction for autonomous vehicles has become a major area of research. The primary method for achieving end to end steering was to use computer vision models on a live feed of video data. However, to further increase accuracy, many companies have added data from light detection and ranging (LiDAR) and or radar sensors through sensor fusion. However, the addition of lasers and sensors comes at a high financial cost. In this paper, I address both of these issues by increasing the accuracy of the computer vision models without the increased cost of using LiDAR and or sensors. I achieved this by improving the accuracy of computer vision models by sensor fusing CAN bus data, a vehicle protocol, with video data. CAN bus data is a rich source of information about the vehicle's state, including its speed, steering angle, and acceleration. By fusing this data with video data, the accuracy of the computer vision model's predictions can be improved. When I trained the model without CAN bus data, I obtained an RMSE of 0.02492, while the model trained with the CAN bus data achieved an RMSE of 0.01970. This finding indicates that fusing CAN Bus data with video data can reduce the computer vision model's prediction error by 20% with some models decreasing the error by 80%.

Ravisri Valluri, Akash Kumar Mohankumar, Kushal Dave et al.

Generative Retrieval introduces a new approach to Information Retrieval by reframing it as a constrained generation task, leveraging recent advancements in Autoregressive (AR) language models. However, AR-based Generative Retrieval methods suffer from high inference latency and cost compared to traditional dense retrieval techniques, limiting their practical applicability. This paper investigates fully Non-autoregressive (NAR) language models as a more efficient alternative for generative retrieval. While standard NAR models alleviate latency and cost concerns, they exhibit a significant drop in retrieval performance (compared to AR models) due to their inability to capture dependencies between target tokens. To address this, we question the conventional choice of limiting the target token space to solely words or sub-words. We propose PIXAR, a novel approach that expands the target vocabulary of NAR models to include multi-word entities and common phrases (up to 5 million tokens), thereby reducing token dependencies. PIXAR employs inference optimization strategies to maintain low inference latency despite the significantly larger vocabulary. Our results demonstrate that PIXAR achieves a relative improvement of 31.0% in MRR@10 on MS MARCO and 23.2% in Hits@5 on Natural Questions compared to standard NAR models with similar latency and cost. Furthermore, online A/B experiments on a large commercial search engine show that PIXAR increases ad clicks by 5.08% and revenue by 4.02%.

Anshul Mittal, Shikhar Mohan, Deepak Saini et al.

Deep extreme classification (XC) aims to train an encoder architecture and an accompanying classifier architecture to tag a data point with the most relevant subset of labels from a very large universe of labels. XC applications in ranking, recommendation and tagging routinely encounter tail labels for which the amount of training data is exceedingly small. Graph convolutional networks (GCN) present a convenient but computationally expensive way to leverage task metadata and enhance model accuracies in these settings. This paper formally establishes that in several use cases, the steep computational cost of GCNs is entirely avoidable by replacing GCNs with non-GCN architectures. The paper notices that in these settings, it is much more effective to use graph data to regularize encoder training than to implement a GCN. Based on these insights, an alternative paradigm RAMEN is presented to utilize graph metadata in XC settings that offers significant performance boosts with zero increase in inference computational costs. RAMEN scales to datasets with up to 1M labels and offers prediction accuracy up to 15% higher on benchmark datasets than state of the art methods, including those that use graph metadata to train GCNs. RAMEN also offers 10% higher accuracy over the best baseline on a proprietary recommendation dataset sourced from click logs of a popular search engine. Code for RAMEN will be released publicly.

Jogendra Nath Kundu, Akshay Kulkarni, Amit Singh et al.

Unsupervised domain adaptation (DA) has gained substantial interest in semantic segmentation. However, almost all prior arts assume concurrent access to both labeled source and unlabeled target, making them unsuitable for scenarios demanding source-free adaptation. In this work, we enable source-free DA by partitioning the task into two: a) source-only domain generalization and b) source-free target adaptation. Towards the former, we provide theoretical insights to develop a multi-head framework trained with a virtually extended multi-source dataset, aiming to balance generalization and specificity. Towards the latter, we utilize the multi-head framework to extract reliable target pseudo-labels for self-training. Additionally, we introduce a novel conditional prior-enforcing auto-encoder that discourages spatial irregularities, thereby enhancing the pseudo-label quality. Experiments on the standard GTA5-to-Cityscapes and SYNTHIA-to-Cityscapes benchmarks show our superiority even against the non-source-free prior-arts. Further, we show our compatibility with online adaptation enabling deployment in a sequentially changing environment.

Akash Kumar Mohankumar, Nikit Begwani, Amit Singh

Retrieving keywords (bidwords) with the same intent as query, referred to as close variant keywords, is of prime importance for effective targeted search advertising. For head and torso search queries, sponsored search engines use a huge repository of same intent queries and keywords, mined ahead of time. Online, this repository is used to rewrite the query and then lookup the rewrite in a repository of bid keywords contributing to significant revenue. Recently generative retrieval models have been shown to be effective at the task of generating such query rewrites. We observe two main limitations of such generative models. First, rewrites generated by these models exhibit low lexical diversity, and hence the rewrites fail to retrieve relevant keywords that have diverse linguistic variations. Second, there is a misalignment between the training objective - the likelihood of training data, v/s what we desire - improved quality and coverage of rewrites. In this work, we introduce CLOVER, a framework to generate both high-quality and diverse rewrites by optimizing for human assessment of rewrite quality using our diversity-driven reinforcement learning algorithm. We use an evaluation model, trained to predict human judgments, as the reward function to finetune the generation policy. We empirically show the effectiveness of our proposed approach through offline experiments on search queries across geographies spanning three major languages. We also perform online A/B experiments on Bing, a large commercial search engine, which shows (i) better user engagement with an average increase in clicks by 12.83% accompanied with an average defect reduction by 13.97%, and (ii) improved revenue by 21.29%.

Junhan Yang, Zheng Liu, Shitao Xiao et al.

The representation learning on textual graph is to generate low-dimensional embeddings for the nodes based on the individual textual features and the neighbourhood information. Recent breakthroughs on pretrained language models and graph neural networks push forward the development of corresponding techniques. The existing works mainly rely on the cascaded model architecture: the textual features of nodes are independently encoded by language models at first; the textual embeddings are aggregated by graph neural networks afterwards. However, the above architecture is limited due to the independent modeling of textual features. In this work, we propose GraphFormers, where layerwise GNN components are nested alongside the transformer blocks of language models. With the proposed architecture, the text encoding and the graph aggregation are fused into an iterative workflow, {making} each node's semantic accurately comprehended from the global perspective. In addition, a {progressive} learning strategy is introduced, where the model is successively trained on manipulated data and original data to reinforce its capability of integrating information on graph. Extensive evaluations are conducted on three large-scale benchmark datasets, where GraphFormers outperform the SOTA baselines with comparable running efficiency.

Albert Haque, Michelle Guo, Alexandre Alahi et al.

One in twenty-five patients admitted to a hospital will suffer from a hospital acquired infection. If we can intelligently track healthcare staff, patients, and visitors, we can better understand the sources of such infections. We envision a smart hospital capable of increasing operational efficiency and improving patient care with less spending. In this paper, we propose a non-intrusive vision-based system for tracking people's activity in hospitals. We evaluate our method for the problem of measuring hand hygiene compliance. Empirically, our method outperforms existing solutions such as proximity-based techniques and covert in-person observational studies. We present intuitive, qualitative results that analyze human movement patterns and conduct spatial analytics which convey our method's interpretability. This work is a step towards a computer-vision based smart hospital and demonstrates promising results for reducing hospital acquired infections.