Peer Revenue Play credits. Real papers.

Papers

Fresh from arXiv, typeset properly. Highlighted words trade on the market.

Computer Science Machine Learning

cs.LG Watch Machine Learning (sign in to use)

Monday 16 February

Machine Learning · Cross-listed from cs.CL

SpreadsheetArena: Decomposing Preference in LLM Generation of Spreadsheet Workbooks

We consider the task of end-to-end spreadsheet generation, where language models produce spreadsheet artifacts to satisfy users' explicit and implicit constraints, specified in natural language. We introduce SpreadsheetArena, a platform for evaluating models' performance on the task via blind pairwise preference votes of LLM-generated spreadsheet workbooks. As with other complex, open-ended tasks, relevant evaluation criteria can vary greatly across use cases, often in ways that are difficult to formalize. Compared to general dialogue or text generation settings, spreadsheet generation presents unique challenges and opportunities: the task output structure is well-defined and multi-dimensional, and there are often complex interactivity and layout considerations. We observe that stylistic, structural, and functional features of preferred spreadsheets vary meaningfully across prompts. Expert evaluations of spreadsheets for finance prompts suggest that even highly ranked models do not reliably produce spreadsheets aligned with domain-specific best practices. We host a live arena and release a dataset of prompts, generated spreadsheets, and preference votes, which we hope will facilitate further study of tasks operating over spreadsheets as a challenging and interesting class of complex, open-ended tasks for LLMs.
Read the full abstract

All authors Srivatsa Kundurthy, Clara Na, Michael Handley, Zach Kirshner, Chen Bo Calvin Zhang, Manasi Sharma, Emma Strubell, John Ling

Machine Learning · Cross-listed from cs.CL

Leveraging Wikidata for Geographically Informed Sociocultural Bias Dataset Creation: Application to Latin America

Large Language Models (LLMs) exhibit inequalities with respect to various cultural contexts. Most prominent open-weights models are trained on Global North data and show prejudicial behavior towards other cultures. Moreover, there is a notable lack of resources to detect biases in non-English languages, especially from Latin America (Latam), a continent containing various cultures, even though they share a common cultural ground. We propose to leverage the content of Wikipedia, the structure of the Wikidata knowledge graph, and expert knowledge from social science in order to create a dataset of question/answer (Q/As) pairs, based on the different popular and social cultures of various Latin American countries. We create the LatamQA database of over 26k questions and associated answers extracted from 26k Wikipedia articles, and transformed into multiple-choice questions (MCQ) in Spanish and Portuguese, in turn translated to English. We use this MCQ to quantify the degree of knowledge of various LLMs and find out (i) a discrepancy in performances between the Latam countries, ones being easier than others for the majority of the models, (ii) that the models perform better in their original language, and (iii) that Iberian Spanish culture is better known than Latam one.
Read the full abstract

All authors Yannis Karmim, Renato Pino, Hernan Contreras, Hernan Lira, Sebastian Cifuentes, Simon Escoffier, Luis Martí, Djamé Seddah, Valentin Barrière

Machine Learning · Cross-listed from cs.CL

Beyond the Prompt in Large Language Models: Comprehension, In-Context Learning, and Chain-of-Thought

Large Language Models (LLMs) have demonstrated remarkable proficiency across diverse tasks, exhibiting emergent properties such as semantic prompt comprehension, In-Context Learning (ICL), and Chain-of-Thought (CoT) reasoning. Despite their empirical success, the theoretical mechanisms driving these phenomena remain poorly understood. This study dives into the foundations of these observations by addressing three critical questions: (1) How do LLMs accurately decode prompt semantics despite being trained solely on a next-token prediction objective? (2) Through what mechanism does ICL facilitate performance gains without explicit parameter updates? and (3) Why do intermediate reasoning steps in CoT prompting effectively unlock capabilities for complex, multi-step problems? Our results demonstrate that, through the autoregressive process, LLMs are capable of exactly inferring the transition probabilities between tokens across distinct tasks using provided prompts. We show that ICL enhances performance by reducing prompt ambiguity and facilitating posterior concentration on the intended task. Furthermore, we find that CoT prompting activates the model's capacity for task decomposition, breaking complex problems into a sequence of simpler sub-tasks that the model has mastered during the pretraining phase. By comparing their individual error bounds, we provide novel theoretical insights into the statistical superiority of advanced prompt engineering techniques.
Read the full abstract

All authors Yuling Jiao, Yanming Lai, Huazhen Lin, Wensen Ma, Houduo Qi, Defeng Sun

Machine Learning

Thin Keys, Full Values: Reducing KV Cache via Low-Dimensional Attention Selection

Standard Transformer attention uses identical dimensionality for queries, keys, and values, yet these components serve different roles: queries and keys produce scalar attention weights (selection), while values carry rich representations (value transfer). We show that selection requires only $O(\log N)$ dimensions to distinguish among $N$ relevant token categories (e.g., syntactic roles, semantic clusters, positional patterns) – far fewer than value transfer needs. We introduce factored keys, which exploit this asymmetry to physically shrink the KV cache of any pretrained model without retraining from scratch – unlike Grouped-Query Attention (GQA) and Multi-Head Latent Attention (MLA), which must be designed into the architecture before pretraining. We factorize each key projection $W_K \approx A_{d \times r} B_{r \times d}$ via truncated singular value decomposition (SVD) (where $r$ is the chosen compression dimension), set $W_K' = A$ as the new key projection producing compact $r$-dimensional keys for the cache, and absorb $B^\top$ into the query projection ($W_Q' = W_Q B^\top$) at zero cost – since queries are never cached. At the 7B scale, training from scratch with $r = d/4$ (where $d$ is the model dimension) matches full-attention perplexity ($9.24$ vs $9.25$ PPL after 20B tokens, mean over two seeds) while using 12% fewer parameters and training 8% faster. For existing models, SVD followed by QK fine-tuning (3 epochs, less than 1% of pretraining data) achieves 75% key cache savings at roughly 2% quality cost on both GPT-2 and Mistral-7B. The approach composes with GQA and quantization for up to $16\times$ combined key cache compression. For a 7B model serving a 128K context, factored keys save 25 GB of KV cache per user, enabling roughly 60% more concurrent users on identical hardware.
Read the full abstract

All authors Hengshuai Yao, Xing Chen, Ahmed Murtadha, Guan Wang

Machine Learning

Delta-Crosscoder: Robust Crosscoder Model Diffing in Narrow Fine-Tuning Regimes

Model diffing methods aim to identify how fine-tuning changes a model's internal representations. Crosscoders approach this by learning shared dictionaries of interpretable latent directions between base and fine-tuned models. However, existing formulations struggle with narrow fine-tuning, where behavioral changes are localized and asymmetric. We introduce Delta-Crosscoder, which combines BatchTopK sparsity with a delta-based loss prioritizing directions that change between models, plus an implicit contrastive signal from paired activations on matched inputs. Evaluated across 10 model organisms, including synthetic false facts, emergent misalignment, subliminal learning, and taboo word guessing (Gemma, LLaMA, Qwen; 1B-9B parameters), Delta-Crosscoder reliably isolates latent directions causally responsible for fine-tuned behaviors and enables effective mitigation, outperforming SAE-based baselines, while matching the Non-SAE-based. Our results demonstrate that crosscoders remain a powerful tool for model diffing.
Read the full abstract

All authors Aly Kassem, Thomas Jiralerspong, Negar Rostamzadeh, Golnoosh Farnadi

Machine Learning · Cross-listed from cs.NI

Data-Driven Optimization of Multi-Generational Cellular Networks: A Performance Classification Framework for Strategic Infrastructure Management

The exponential growth in mobile data demand necessitates intelligent management of telecommunications infrastructure to ensure Quality of Service (QoS) and operational efficiency. This paper presents a comprehensive analysis of a multigenerational cellular network dataset, sourced from the OpenCelliD project, to identify patterns in network deployment, utilization, and infrastructure gaps. The methodology involves geographical, temporal, and performance analysis of 1,818 cell tower entries, predominantly Long Term Evolution (LTE), across three countries with a significant concentration in Pakistan. Key findings reveal the long-term persistence of legacy 2G/3G infrastructure in major urban centers, the existence of a substantial number of under-utilized towers representing opportunities for cost savings, and the identification of specific "non-4G demand zones" where active user bases are served by outdated technologies. By introducing a signal-density metric, we distinguish between absolute over-utilization and localized congestion. The results provide actionable intelligence for Mobile Network Operators (MNOs) to guide strategic LTE upgrades, optimize resource allocation, and bridge the digital divide in underserved regions.
Read the full abstract

Machine Learning · Cross-listed from cs.NI

When Scaling Fails: Network and Fabric Effects on Distributed GPU Training Performance

Scaling distributed GPU training is commonly assumed to yield predictable performance gains as additional nodes are added. In practice, many large-scale deployments encounter diminishing returns and unstable behavior well before theoretical limits are reached. This paper examines why scaling fails in real systems, with a focus on the role of network and fabric effects that are often overlooked by higher-level training frameworks. We present an empirical study of distributed GPU training performance across multiple production-scale clusters. Our results show that network topology, congestion dynamics, collective synchronization behavior, and GPU locality frequently dominate end-to-end training performance once workloads move beyond a small number of nodes. Identical models and software stacks can exhibit sharply different scaling characteristics depending on fabric design and runtime communication patterns. We identify recurring failure modes that emerge as training transitions from single-node to multi-node execution, including synchronization amplification, topology-induced contention, and locality-driven performance variance. These effects are often invisible to standard profiling tools and are therefore misdiagnosed as framework or model-level inefficiencies. Based on these findings, we outline practical diagnostic principles that system builders can apply to understand scaling limits, improve predictability, and reduce the cost of large-scale distributed training.
Read the full abstract

Machine Learning · Cross-listed from eess.SP

High-Resolution Range Profile Classifiers Require Aspect-Angle Awareness

We revisit High-Resolution Range Profile (HRRP) classification with aspect-angle conditioning. While prior work often assumes that aspect-angle information is incomplete during training or unavailable at inference, we study a setting where angles are available for all training samples and explicitly provided to the classifier. Using three datasets and a broad range of conditioning strategies and model architectures, we show that both single-profile and sequential classifiers benefit consistently from aspect-angle awareness, with an average accuracy gain of about 7% and improvements of up to 10%, depending on the model and dataset. In practice, aspect angles are not directly measured and must be estimated. We show that a causal Kalman filter can estimate them online with a median error of 5{\textdegree}, and that training and inference with estimated angles preserves most of the gains, supporting the proposed approach in realistic conditions.
Read the full abstract

Machine Learning

Fast and Effective On-policy Distillation from Reasoning Prefixes

On-policy distillation (OPD), which samples trajectories from the student model and supervises them with a teacher at the token level, avoids relying solely on verifiable terminal rewards and can yield better generalization than off-policy distillation. However, OPD requires expensive on-the-fly sampling of the student policy during training, which substantially increases training cost, especially for long responses. Our initial analysis shows that, during OPD, training signals are often concentrated in the prefix of each output, and that even a short teacher-generated prefix can significantly help the student produce the correct answer. Motivated by these observations, we propose a simple yet effective modification of OPD: we apply the distillation objective only to prefixes of student-generated outputs and terminate each sampling early during distillation. Experiments on a suite of AI-for-Math and out-of-domain benchmarks show that on-policy prefix distillation matches the performance of full OPD while reducing training FLOP by 2x-47x.
Read the full abstract

All authors Dongxu Zhang, Zhichao Yang, Sepehr Janghorbani, Jun Han, Andrew Ressler II, Qian Qian, Gregory D. Lyng, Sanjit Singh Batra, Robert E. Tillman

Machine Learning · Cross-listed from cs.CY

Knowing Isn't Understanding: Re-grounding Generative Proactivity with Epistemic and Behavioral Insight

Generative AI agents equate understanding with resolving explicit queries, an assumption that confines interaction to what users can articulate. This assumption breaks down when users themselves lack awareness of what is missing, risky, or worth considering. In such conditions, proactivity is not merely an efficiency enhancement, but an epistemic necessity. We refer to this condition as epistemic incompleteness: where progress depends on engaging with unknown unknowns for effective partnership. Existing approaches to proactivity remain narrowly anticipatory, extrapolating from past behavior and presuming that goals are already well defined, thereby failing to support users meaningfully. However, surfacing possibilities beyond a user's current awareness is not inherently beneficial. Unconstrained proactive interventions can misdirect attention, overwhelm users, or introduce harm. Proactive agents, therefore, require behavioral grounding: principled constraints on when, how, and to what extent an agent should intervene. We advance the position that generative proactivity must be grounded both epistemically and behaviorally. Drawing on the philosophy of ignorance and research on proactive behavior, we argue that these theories offer critical guidance for designing agents that can engage responsibly and foster meaningful partnerships.
Read the full abstract

Machine Learning

Scaling Laws for Masked-Reconstruction Transformers on Single-Cell Transcriptomics

Neural scaling laws – power-law relationships between loss, model size, and data – have been extensively documented for language and vision transformers, yet their existence in single-cell genomics remains largely unexplored. We present the first systematic study of scaling behaviour for masked-reconstruction transformers trained on single-cell RNA sequencing (scRNA-seq) data. Using expression profiles from the CELLxGENE Census, we construct two experimental regimes: a data-rich regime (512 highly variable genes, 200,000 cells) and a data-limited regime (1,024 genes, 10,000 cells). Across seven model sizes spanning three orders of magnitude in parameter count (533 to 3.4 x 10^8 parameters), we fit the parametric scaling law to validation mean squared error (MSE). The data-rich regime exhibits clear power-law scaling with an irreducible loss floor of c ~ 1.44, while the data-limited regime shows negligible scaling, indicating that model capacity is not the binding constraint when data are scarce. These results establish that scaling laws analogous to those observed in natural language processing do emerge in single-cell transcriptomics when sufficient data are available, and they identify the data-to-parameter ratio as a critical determinant of scaling behaviour. A preliminary conversion of the data-rich asymptotic floor to information-theoretic units yields an estimate of approximately 2.30 bits of entropy per masked gene position. We discuss implications for the design of single-cell foundation models and outline the additional measurements needed to refine this entropy estimate.
Read the full abstract

Machine Learning · Cross-listed from cs.GT

Decision Making under Imperfect Recall: Algorithms and Benchmarks

In game theory, imperfect-recall decision problems model situations in which an agent forgets information it held before. They encompass games such as the “absentminded driver” and team games with limited communication. In this paper, we introduce the first benchmark suite for imperfect-recall decision problems. Our benchmarks capture a variety of problem types, including ones concerning privacy in AI systems that elicit sensitive information, and AI safety via testing of agents in simulation. Across 61 problem instances generated using this suite, we evaluate the performance of different algorithms for finding first-order optimal strategies in such problems. In particular, we introduce the family of regret matching (RM) algorithms for nonlinear constrained optimization. This class of parameter-free algorithms has enjoyed tremendous success in solving large two-player zero-sum games, but, surprisingly, they were hitherto relatively unexplored beyond that setting. Our key finding is that RM algorithms consistently outperform commonly employed first-order optimizers such as projected gradient descent, often by orders of magnitude. This establishes, for the first time, the RM family as a formidable approach to large-scale constrained optimization problems.
Read the full abstract

All authors Emanuel Tewolde, Brian Hu Zhang, Ioannis Anagnostides, Tuomas Sandholm, Vincent Conitzer

Machine Learning

Size-Transferability of Graph Transformers with Convolutional Positional Encodings

Transformers have achieved remarkable success across domains, motivating the rise of Graph Transformers (GTs) as attention-based architectures for graph-structured data. A key design choice in GTs is the use of Graph Neural Network (GNN)-based positional encodings to incorporate structural information. In this work, we study GTs through the lens of manifold limit models for graph sequences and establish a theoretical connection between GTs with GNN positional encodings and Manifold Neural Networks (MNNs). Building on transferability results for GNNs under manifold convergence, we show that GTs inherit transferability guarantees from their positional encodings. In particular, GTs trained on small graphs provably generalize to larger graphs under mild assumptions. We complement our theory with extensive experiments on standard graph benchmarks, demonstrating that GTs exhibit scalable behavior on par with GNNs. To further show the efficiency in a real-world scenario, we implement GTs for shortest path distance estimation over terrains to better illustrate the efficiency of the transferable GTs. Our results provide new insights into the understanding of GTs and suggest practical directions for efficient training of GTs in large-scale settings.
Read the full abstract

All authors Javier Porras-Valenzuela, Zhiyang Wang, Teresa Shang, Yusu Wang, Alejandro Ribeiro

Machine Learning

Closing the Distribution Gap in Adversarial Training for LLMs

Adversarial training for LLMs is one of the most promising methods to reliably improve robustness against adversaries. However, despite significant progress, models remain vulnerable to simple in-distribution exploits, such as rewriting prompts in the past tense or translating them into other languages. We argue that this persistent fragility stems from a fundamental limitation in current adversarial training algorithms: they minimize adversarial loss on their training set but inadequately cover the data distribution, resulting in vulnerability to seemingly simple attacks. To bridge this gap, we propose Distributional Adversarial Training, DAT. We leverage Diffusion LLMs to approximate the true joint distribution of prompts and responses, enabling generation of diverse, high-likelihood samples that address generalization failures. By combining optimization over the data distribution provided by the diffusion model with continuous adversarial training, DAT achieves substantially higher adversarial robustness than previous methods.
Read the full abstract

All authors Chengzhi Hu, Jonas Dornbusch, David Lüdke, Stephan Günnemann, Leo Schwinn

Machine Learning

BindCLIP: A Unified Contrastive-Generative Representation Learning Framework for Virtual Screening

Virtual screening aims to efficiently identify active ligands from massive chemical libraries for a given target pocket. Recent CLIP-style models such as DrugCLIP enable scalable virtual screening by embedding pockets and ligands into a shared space. However, our analyses indicate that such representations can be insensitive to fine-grained binding interactions and may rely on shortcut correlations in training data, limiting their ability to rank ligands by true binding compatibility. To address these issues, we propose BindCLIP, a unified contrastive-generative representation learning framework for virtual screening. BindCLIP jointly trains pocket and ligand encoders using CLIP-style contrastive learning together with a pocket-conditioned diffusion objective for binding pose generation, so that pose-level supervision directly shapes the retrieval embedding space toward interaction-relevant features. To further mitigate shortcut reliance, we introduce hard-negative augmentation and a ligand-ligand anchoring regularizer that prevents representation collapse. Experiments on two public benchmarks demonstrate consistent improvements over strong baselines. BindCLIP achieves substantial gains on challenging out-of-distribution virtual screening and improves ligand-analogue ranking on the FEP+ benchmark. Together, these results indicate that integrating generative, pose-level supervision with contrastive learning yields more interaction-aware embeddings and improves generalization in realistic screening settings, bringing virtual screening closer to real-world applicability.
Read the full abstract

All authors Anjie Qiao, Zhen Wang, Yaliang Li, Jiahua Rao, Yuedong Yang

Machine Learning

tensorFM: Low-Rank Approximations of Cross-Order Feature Interactions

We address prediction problems on tabular categorical data, where each instance is defined by multiple categorical attributes, each taking values from a finite set. These attributes are often referred to as fields, and their categorical values as features. Such problems frequently arise in practical applications, including click-through rate prediction and social sciences. We introduce and analyze {tensorFM}, a new model that efficiently captures high-order interactions between attributes via a low-rank tensor approximation representing the strength of these interactions. Our model generalizes field-weighted factorization machines. Empirically, tensorFM demonstrates competitive performance with state-of-the-art methods. Additionally, its low latency makes it well-suited for time-sensitive applications, such as online advertising.
Read the full abstract

All authors Alessio Mazzetto, Mohammad Mahdi Khalili, Laura Fee Nern, Michael Viderman, Alex Shtoff, Krzysztof Dembczyński

Machine Learning

Automatically Finding Reward Model Biases

Reward models are central to large language model (LLM) post-training. However, past work has shown that they can reward spurious or undesirable attributes such as length, format, hallucinations, and sycophancy. In this work, we introduce and study the research problem of automatically finding reward model biases in natural language. We offer a simple approach of using an LLM to iteratively propose and refine candidate biases. Our method can recover known biases and surface novel ones: for example, we found that Skywork-V2-8B, a leading open-weight reward model, often mistakenly favors responses with redundant spacing and responses with hallucinated content. In addition, we show evidence that evolutionary iteration outperforms flat best-of-N search, and we validate the recall of our pipeline using synthetically injected biases. We hope our work contributes to further research on improving RMs through automated interpretability methods.
Read the full abstract

Machine Learning

ÜberWeb: Insights from Multilingual Curation for a 20-Trillion-Token Dataset

Multilinguality is a core capability for modern foundation models, yet training high-quality multilingual models remains challenging due to uneven data availability across languages. A further challenge is the performance interference that can arise from joint multilingual training, commonly referred to as the "curse of multilinguality". We study multilingual data curation across thirteen languages and find that many reported regressions are not inherent to multilingual scaling but instead stem from correctable deficiencies in data quality and composition rather than fundamental capacity limits. In controlled bilingual experiments, improving data quality for any single language benefits others: curating English improves non-English performance in 12 of 13 languages, while curating non-English yields reciprocal improvements in English. Bespoke per-language curation produces substantially larger within-language improvements. Extending these findings to large-scale general-purpose training mixtures, we show that curated multilingual allocations comprising under 8% of total tokens remain remarkably effective. We operationalize this approach within an effort that produced a 20T-token pretraining corpus derived entirely from public sources. Models with 3B and 8B parameters trained on a 1T-token random subset achieve competitive multilingual accuracy with 4-10x fewer training FLOPs than strong public baselines, establishing a new Pareto frontier in multilingual performance versus compute. Moreover, these benefits extend to frontier model scale: the 20T-token corpus served as part of the pretraining dataset for Trinity Large (400B/A13B), which exhibits strong multilingual performance relative to its training FLOPs. These results show that targeted, per-language data curation mitigates multilingual interference and enables compute-efficient multilingual scaling.
Read the full abstract

All authors DatologyAI: Aldo Gael Carranza, Kaleigh Mentzer, Ricardo Pio Monti, Alex Fang, Alvin Deng, Amro Abbas, Anshuman Suri, Brett Larsen, Cody Blakeney, Darren Teh, David Schwab, Diego Kiner, Fan Pan, Haakon Mongstad, Haoli Yin, Jack Urbanek, Jason Lee, Jason Telanoff, Josh Wills, Luke Merrick, Maximilian Böther, Parth Doshi, Paul Burstein, Pratyush Maini, Rishabh Adiga, Siddharth Joshi, Spandan Das, Tony Jiang, Vineeth Dorna, Zhengping Wang, Bogdan Gaza, Ari Morcos, Matthew Leavitt

Machine Learning

MAVRL: Learning Reward Functions from Multiple Feedback Types with Amortized Variational Inference

Reward learning typically relies on a single feedback type or combines multiple feedback types using manually weighted loss terms. Currently, it remains unclear how to jointly learn reward functions from heterogeneous feedback types such as demonstrations, comparisons, ratings, and stops that provide qualitatively different signals. We address this challenge by formulating reward learning from multiple feedback types as Bayesian inference over a shared latent reward function, where each feedback type contributes information through an explicit likelihood. We introduce a scalable amortized variational inference approach that learns a shared reward encoder and feedback-specific likelihood decoders and is trained by optimizing a single evidence lower bound. Our approach avoids reducing feedback to a common intermediate representation and eliminates the need for manual loss balancing. Across discrete and continuous-control benchmarks, we show that jointly inferred reward posteriors outperform single-type baselines, exploit complementary information across feedback types, and yield policies that are more robust to environment perturbations. The inferred reward uncertainty further provides interpretable signals for analyzing model confidence and consistency across feedback types.
Read the full abstract

All authors Raphaël Baur, Yannick Metz, Maria Gkoulta, Mennatallah El-Assady, Giorgia Ramponi, Thomas Kleine Buening

Machine Learning

COMPOT: Calibration-Optimized Matrix Procrustes Orthogonalization for Transformers Compression

Post-training compression of transformer models commonly relies on truncated singular value decomposition (SVD) strategies leading to low-rank approximations of the original model weights. However, the underlying single shared subspace modeling can degrade accuracy even at moderate compression. Sparse dictionary learning provides a more flexible union-of-subspaces representation, but existing approaches often suffer from costly iterative dictionary and coefficient updates. We propose $\textbf{COMPOT}$ ($\textbf{C}$alibration-$\textbf{O}$ptimized $\textbf{M}$atrix $\textbf{P}$rocrustes $\textbf{O}$rthogonalization for $\textbf{T}$ransformers), a training-free compression framework that uses a small calibration dataset to estimate a sparse weight factorization. COMPOT employs orthogonal dictionaries that enable closed-form Procrustes updates for the dictionary and analytical single-step sparse coding for the coefficients, reducing significantly the overall optimization cost. To handle heterogeneous layer sensitivity under a global compression budget, COMPOT further introduces a one-shot dynamic allocation strategy that adaptively redistributes layer-wise compression rates. Extensive experiments across diverse architectures and tasks show that COMPOT consistently delivers a superior quality-compression trade-off over strong low-rank and sparse baselines, while remaining fully compatible with post-training quantization for extreme compression.
Read the full abstract

All authors Denis Makhov, Dmitriy Shopkhoev, Magauiya Zhussip, Ammar Ali, Baher Mohammad, Stamatios Lefkimmiatis

Machine Learning · Cross-listed from cs.CR

Weight space Detection of Backdoors in LoRA Adapters

LoRA adapters let users fine-tune large language models (LLMs) efficiently. However, LoRA adapters are shared through open repositories like Hugging Face Hub \citep{huggingface_hub_docs}, making them vulnerable to backdoor attacks. Current detection methods require running the model with test input data – making them impractical for screening thousands of adapters where the trigger for backdoor behavior is unknown. We detect poisoned adapters by analyzing their weight matrices directly, without running the model – making our method trigger-agnostic. For each attention projection (Q, K, V, O), our method extracts five spectral statistics from the low-rank update $\Delta W$, yielding a 20-dimensional signature for each adapter. A logistic regression detector trained on this representation separates benign and poisoned adapters across three model families – Llama-3.2-3B~\citep{llama3}, Qwen2.5-3B~\citep{qwen25}, and Gemma-2-2B~\citep{gemma2} – on unseen test adapters drawn from instruction-following, reasoning, question-answering, code, and classification tasks. Across all three architectures, the detector achieves 100% accuracy.
Read the full abstract

All authors David Puertolas Merenciano, Ekaterina Vasyagina, Kevin Zhu, Javier Ferrando, Maheep Chaudhary

Machine Learning

Learning Data-Efficient and Generalizable Neural Operators via Fundamental Physics Knowledge

Recent advances in scientific machine learning (SciML) have enabled neural operators (NOs) to serve as powerful surrogates for modeling the dynamic evolution of physical systems governed by partial differential equations (PDEs). While existing approaches focus primarily on learning simulations from the target PDE, they often overlook more fundamental physical principles underlying these equations. Inspired by how numerical solvers are compatible with simulations of different settings of PDEs, we propose a multiphysics training framework that jointly learns from both the original PDEs and their simplified basic forms. Our framework enhances data efficiency, reduces predictive errors, and improves out-of-distribution (OOD) generalization, particularly in scenarios involving shifts of physical parameters and synthetic-to-real transfer. Our method is architecture-agnostic and demonstrates consistent improvements in normalized root mean square error (nRMSE) across a wide range of 1D/2D/3D PDE problems. Through extensive experiments, we show that explicit incorporation of fundamental physics knowledge significantly strengthens the generalization ability of neural operators. We will release models and codes at https://sites.google.com/view/sciml-fundemental-pde.
Read the full abstract

All authors Siying Ma, Mehrdad M. Zadeh, Mauricio Soroco, Wuyang Chen, Jiguo Cao, Vijay Ganesh

Machine Learning

Seeing to Generalize: How Visual Data Corrects Binding Shortcuts

Vision Language Models (VLMs) are designed to extend Large Language Models (LLMs) with visual capabilities, yet in this work we observe a surprising phenomenon: VLMs can outperform their underlying LLMs on purely text-only tasks, particularly in long-context information retrieval. To investigate this effect, we build a controlled synthetic retrieval task and find that a transformer trained only on text achieves perfect in-distribution accuracy but fails to generalize out of distribution, while subsequent training on an image-tokenized version of the same task nearly doubles text-only OOD performance. Mechanistic interpretability reveals that visual training changes the model's internal binding strategy: text-only training encourages positional shortcuts, whereas image-based training disrupts them through spatial translation invariance, forcing the model to adopt a more robust symbolic binding mechanism that persists even after text-only examples are reintroduced. We further characterize how binding strategies vary across training regimes, visual encoders, and initializations, and show that analogous shifts occur during pretrained LLM-to-VLM transitions. Our findings suggest that cross-modal training can enhance reasoning and generalization even for tasks grounded in a single modality.
Read the full abstract

All authors Nicolas Buzeta, Felipe del Rio, Cristian Hinostroza, Denis Parra, Hans Lobel, Rodrigo Toro Icarte

Machine Learning · Cross-listed from cs.CV

Time-Archival Camera Virtualization for Sports and Visual Performances

Camera virtualization – an emerging solution to novel view synthesis – holds transformative potential for visual entertainment, live performances, and sports broadcasting by enabling the generation of photorealistic images from novel viewpoints using images from a limited set of calibrated multiple static physical cameras. Despite recent advances, achieving spatially and temporally coherent and photorealistic rendering of dynamic scenes with efficient time-archival capabilities, particularly in fast-paced sports and stage performances, remains challenging for existing approaches. Recent methods based on 3D Gaussian Splatting (3DGS) for dynamic scenes could offer real-time view-synthesis results. Yet, they are hindered by their dependence on accurate 3D point clouds from the structure-from-motion method and their inability to handle large, non-rigid, rapid motions of different subjects (e.g., flips, jumps, articulations, sudden player-to-player transitions). Moreover, independent motions of multiple subjects can break the Gaussian-tracking assumptions commonly used in 4DGS, ST-GS, and other dynamic splatting variants. This paper advocates reconsidering a neural volume rendering formulation for camera virtualization and efficient time-archival capabilities, making it useful for sports broadcasting and related applications. By modeling a dynamic scene as rigid transformations across multiple synchronized camera views at a given time, our method performs neural representation learning, providing enhanced visual rendering quality at test time. A key contribution of our approach is its support for time-archival, i.e., users can revisit any past temporal instance of a dynamic scene and can perform novel view synthesis, enabling retrospective rendering for replay, analysis, and archival of live events, a functionality absent in existing neural rendering approaches and novel view synthesis...
Read the full abstract

2602.15181 · 16 Feb · Project Page: https://yunxiaozhangjack.com/tacv/; Under minor revision in Journal of Computer Vision and Image Understanding (CVIU); Special Issue: Computer Vision for Sports and Winter Sports. Outcome of a master and bachelor student project completed in Visual and Spatial AI Lab at TAMU

Machine Learning · Cross-listed from hep-th

Learning the S-matrix from data: Rediscovering gravity from gauge theory via symbolic regression

We demonstrate that modern machine-learning methods can autonomously reconstruct several flagship analytic structures in scattering amplitudes directly from numerical on-shell data. In particular, we show that the Kawai–Lewellen–Tye (KLT) relations can be rediscovered using symbolic regression applied to colour-ordered Yang–Mills amplitudes with Mandelstam invariants as input features. Using standard feature-selection techniques, specifically column-pivoted QR factorisation, we simultaneously recover the Kleiss–Kuijf and Bern–Carrasco–Johansson (BCJ) relations, identifying a minimal basis of partial amplitudes without any group-theoretic input. We obtain the tree-level KLT relations with high numerical accuracy up to five external legs, using only minimal theoretical priors, and we comment on the obstacles to generalising the method to higher multiplicity. Our results establish symbolic regression as a practical tool for exploring the analytic structure of the scattering-amplitude landscape, and suggests a general data-driven strategy for uncovering hidden relations in general theories. For comparison, we benchmark this general approach with a recently introduced neural-network based method.
Read the full abstract

Machine Learning · Cross-listed from cs.CR

Exploiting Layer-Specific Vulnerabilities to Backdoor Attack in Federated Learning

Federated learning (FL) enables distributed model training across edge devices while preserving data locality. This decentralized approach has emerged as a promising solution for collaborative learning on sensitive user data, effectively addressing the longstanding privacy concerns inherent in centralized systems. However, the decentralized nature of FL exposes new security vulnerabilities, especially backdoor attacks that threaten model integrity. To investigate this critical concern, this paper presents the Layer Smoothing Attack (LSA), a novel backdoor attack that exploits layer-specific vulnerabilities in neural networks. First, a Layer Substitution Analysis methodology systematically identifies backdoor-critical (BC) layers that contribute most significantly to backdoor success. Subsequently, LSA strategically manipulates these BC layers to inject persistent backdoors while remaining undetected by state-of-the-art defense mechanisms. Extensive experiments across diverse model architectures and datasets demonstrate that LSA achieves a remarkably backdoor success rate of up to 97% while maintaining high model accuracy on the primary task, consistently bypassing modern FL defenses. These findings uncover fundamental vulnerabilities in current FL security frameworks, demonstrating that future defenses must incorporate layer-aware detection and mitigation strategies.
Read the full abstract

All authors Mohammad Hadi Foroughi, Seyed Hamed Rastegar, Mohammad Sabokrou, Ahmad Khonsari

Machine Learning

Learning Representations from Incomplete EHR Data with Dual-Masked Autoencoding

Electronic health records (EHR) arrive masked. Clinicians order measurements selectively, and any patient table thus contains only a subset of the values that characterize the underlying physiological state. Prior masked modeling approaches on EHR data either impute the table before learning, represent missingness through a dedicated placeholder signal, or optimize solely for imputation, which limits the representations they learn for downstream clinical tasks and carries every unobserved entry through the encoder. We introduce AID-MAE, an Augmented-Intrinsic Dual-Masked Autoencoder that learns directly from incomplete tables by combining the intrinsic mask the record already carries with an augmented mask that hides a subset of observed values for reconstruction during pretraining. Neither type of masked entry enters the encoder, so attention operates only over what was observed. AID-MAE achieves consistent improvements over strong baselines across multiple clinical tasks on two datasets. Across experiments, we discuss that recovering the missing entries is not a prerequisite for learning and show that the representations learned carry clinical structure without supervision.
Read the full abstract

All authors Xiao Xiang, David Restrepo, Hyewon Jeong, Yugang Jia, Leo Anthony Celi

Machine Learning

Refine Now, Query Fast: A Decoupled Refinement Paradigm for Implicit Neural Fields

Implicit Neural Representations (INRs) have emerged as promising surrogates for large 3D scientific simulations due to their ability to continuously model spatial and conditional fields, yet they face a critical fidelity-speed dilemma: deep MLPs suffer from high inference cost, while efficient embedding-based models lack sufficient expressiveness. To resolve this, we propose the Decoupled Representation Refinement (DRR) architectural paradigm. DRR leverages a deep refiner network, alongside non-parametric transformations, in a one-time offline process to encode rich representations into a compact and efficient embedding structure. This approach decouples slow neural networks with high representational capacity from the fast inference path. We introduce DRR-Net, a simple network that validates this paradigm, and a novel data augmentation strategy, Variational Pairs (VP) for improving INRs under complex tasks like high-dimensional surrogate modeling. Experiments on several ensemble simulation datasets demonstrate that our approach achieves state-of-the-art fidelity, while being up to 27$\times$ faster at inference than high-fidelity baselines and remaining competitive with the fastest models. The DRR paradigm offers an effective strategy for building powerful and practical neural field surrogates and INRs in broader applications, with a minimal compromise between speed and quality.
Read the full abstract

Machine Learning · Cross-listed from cs.CV

Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories

Reliable video understanding requires high-quality video datasets that can provide both precise semantic labels and temporally consistent annotations. Detecting annotation errors in densely labeled videos is challenging because errors may arise from semantic **mislabeling**, where labels disagree with visual content, or temporal **disordering**, where otherwise plausible labels violate procedural progression. Training dynamics have been used to identify mislabeled training examples primarily for static samples. We investigate checkpoint loss dynamics for **out-of-sample auditing** of temporally annotated videos. We compute **Cumulative Sample Loss (CSL)** as the mean annotation-conditioned loss of an audit frame across checkpoints trained on a *disjoint* reference set. CSL acts as a dynamic fingerprint and captures the persistent disagreement between its annotation and learned visual-temporal structure. High-CSL frames are then flagged as likely candidates for potential annotation errors, including semantic mislabeling or temporal disordering. Experiments on EgoPER and Cholec80 show that CSL substantially outperforms final-checkpoint loss and achieves up to a **4.2-point AUC improvement** over prior baselines on EgoPER and **92.0/78.5 AUC** for mislabeling/disordering on Cholec80. These results demonstrate checkpoint loss dynamics as an effective diagnostic for temporal annotation auditing.
Read the full abstract

All authors Praditha Alwis, Soumyadeep Chandra, Deepak Ravikumar, Kaushik Roy

Machine Learning · Cross-listed from quant-ph

Beyond Reinforcement Learning: Fast and Scalable Quantum Circuit Synthesis

Quantum unitary synthesis addresses the problem of translating abstract quantum algorithms into sequences of hardware-executable quantum gates. Solving this task exactly is infeasible in general due to the exponential growth of the underlying combinatorial search space. Existing approaches suffer from misaligned optimization objectives, substantial training costs and limited generalization across different qubit counts. We mitigate these limitations by using supervised learning to approximate the minimum description length of residual unitaries and combining this estimate with stochastic beam search to identify near optimal gate sequences. Our method relies on a lightweight model with zero-shot generalization, substantially reducing training overhead compared to prior baselines. Across multiple benchmarks, we achieve faster wall-clock synthesis times while exceeding state-of-the-art methods in terms of success rate for complex circuits.
Read the full abstract

All authors Lukas Theißinger, Thore Gerlach, David Berghaus, Christian Bauckhage