论文检索

Applications · Everything Else

Gyeongwon J Kim, Alex Wilf, Louis-Philippe Morency, Daniel Fried

Recent progress in autonomous code generation has fueled excitement around AI agents capable of accelerating scientific discovery by running experiments. However, there is currently no benchmark that evaluates whether such agents can implement scientific ideas when given varied amounts of code as a starting point, interpolating between reproduction (running code) and from-scratch replication (fully re-implementing and running code). We introduce AutoExperiment, a benchmark that evaluates AI agents’ ability to implement and run machine learning experiments based on natural language descriptions in research papers. In each task, agents are given a research paper, a codebase with key functions masked out, and a command to run the experiment. The goal is to generate the missing code, execute the experiment in a sandboxed environment, and reproduce the results. AutoExperiment scales in difficulty by varying the number of missing functions $n$, ranging from partial reproduction to full replication. We evaluate state-of-the-art agents and find that performance degrades rapidly as $n$ increases. Agents that can dynamically interact with the environment (e.g. to debug their code) can outperform agents in fixed ``agentless'' harnesses, and there exists a significant gap between single-shot and multi-trial success rates (Pass@1 vs. Pass@5), motivating verifier approaches to our benchmark. Our findings highlight critical challenges in long-horizon code generation, context retrieval, and autonomous experiment execution, establishing AutoExperiment as a new benchmark for evaluating progress in AI-driven scientific experimentation. Our data and code are open-sourced at https://github.com/j1mk1m/AutoExperiment.

Social Aspects · Accountability, Transparency and Interpretability

Yupu Gu, Rongzhe Wei, Andy Zhu, Pan Li

Knowledge editing (KE) is crucial for making precise modifications to factual knowledge within large language models (LLMs). Existing KE methods, however, are primarily designed for dense architectures, limiting their applicability to the increasingly popular sparse Mixture-of-Experts (MoE) models that power modern scalable LLMs. While MoEs offer remarkable efficiency and capacity scaling, their unique structure introduces new challenges for KE. Naively adapting dense-model editors to MoEs is not only computationally expensive but also induces routing distribution shifts that degrade model stability and consistency. To address these challenges, we introduce MoEEdit, the first systematic framework for routing-stable knowledge editing in MoE LLMs. Our approach reparameterizes expert updates through per-expert null-space projections, ensuring router inputs remain invariant to suppress these shifts, and solves the resulting block-structured optimization with an efficient block coordinate descent (BCD) solver. Experiments demonstrate that MoEEdit achieves state-of-the-art efficacy and generalization, while maintaining high specificity, routing stability, and superior computational and memory efficiency. Our work establishes a robust foundation for scalable and precise knowledge editing in modern sparse LLMs by highlighting the necessity of routing-stable interventions.

Social Aspects · Trustworthy Machine Learning

Xinjie Shen, Mufei Li, Pan Li

The deployment of Large Language Models (LLMs) in embodied agents creates an urgent need to measure their privacy awareness in the physical world. Existing evaluation methods, however, are confined to natural language based scenarios. To bridge this gap, we introduce EAPrivacy, a comprehensive evaluation benchmark designed to quantify the physical-world privacy awareness of LLM-powered agents. EAPrivacy utilizes procedurally generated scenarios across four tiers to test an agent's ability to handle sensitive objects, adapt to changing environments, balance task execution with privacy constraints, and resolve conflicts with social norms. Our measurements reveal a critical deficit in current models. The top-performing model, Gemini 2.5 Pro, achieved only 59\% accuracy in scenarios involving changing physical environments. Furthermore, when a task was accompanied by a privacy request, models prioritized completion over the constraint in up to 86\% of cases. In high-stakes situations pitting privacy against critical social norms, leading models like GPT-4o and Claude-3.5-haiku disregarded the social norm over 15\% of the time. These findings, demonstrated by our benchmark, underscore a fundamental misalignment in LLMs regarding physically grounded privacy and establish the need for more robust, physically-aware alignment. Datasets are available at https://github.com/Graph-COM/EAPrivacy

General Machine Learning · Representation Learning

Gabriel Y. Arteaga, Marius Aasan, Rwiddhi Chakraborty, Martine Hjelkrem-Tan, Thalles Santos Silva, Michael Kampffmeyer, Adín Ramírez Rivera

Prototypical self-supervised learning methods consistently suffer from partial prototype collapse, where multiple prototypes converge to nearly identical representations. This undermines their central purpose—providing diverse and informative targets to guide encoders toward rich representations—and has led practitioners to over-parameterize prototype sets or add ad-hoc regularizers, which mitigate symptoms rather than address the root cause. We empirically trace the collapse to the joint optimization of encoders and prototypes, which encourages a type of shortcut learning: early in training prototypes drift toward redundant representations that minimize loss without necessarily enhancing representation diversity. To break the joint optimization, we introduce a fully decoupled training strategy that learns prototypes and encoders under separate objectives. Concretely, we model prototypes as a Gaussian mixture updated with an online EM-style procedure, independent of the encoder's loss. This simple yet principled decoupling eliminates prototype collapse without explicit regularization and yields consistently diverse prototypes, which in several settings translate to improved downstream performance.

Theory · Domain Adaptation and Transfer Learning

Wei Feng, Sijin Zhou, Yiwen Jiang, Zongyuan Ge

Continual Category Discovery (CCD) aims to leverage models trained on known categories to automatically discover novel category concepts from continuously arriving streams of unlabeled data, while retaining the ability to recognize previously known classes. Despite recent progress, existing methods often assume that data across all stages are drawn from a single, stationary distribution—a condition rarely satisfied in open-world scenarios. In this paper, we challenge this stationary-distribution assumption by introducing the Open-World Continual Category Discovery (OW-CCD) setting. We address this challenge with PRISM (\underline{P}rogressive \underline{R}obust d\underline{I}scovery under \underline{S}trea\underline{M}ing data), an adaptive continual discovery framework consisting of three key components. First, inspired by spectral properties, we develop a high-frequency-driven category separation technique that exploits high-frequency components—preserving more global information—to distinguish known from unknown categories. Second, for known categories, we design a sparse assignment matching strategy, which performs proximal sparse sample-to-label matching to assign reliable cluster labels to known-class samples. Finally, to better recognize novel categories, we propose an invariant knowledge transfer module that enforces domain-invariant category relation consistency, thereby facilitating robust knowledge transfer from known to unknown classes under domain shifts. Extensive experiments on the SSB-C and DomainNet benchmarks demonstrate that our method significantly outperforms state-of-the-art CCD approaches, highlighting its effectiveness and superiority.

Deep Learning · Attention Mechanisms

Malik Khalaf, Yara Shamshoum, Nitzan Hodos, Yuval Sieradzki, Assaf Schuster

The Multi-Head Attention mechanism is central to LLM operation, and multiple works target its compute and memory efficiency during training. While most works focus on approximating the scaled dot product, the memory consumption of the linear projections that compute the $Q$, $K$, and $V$ tensors from the input $x$ is often overlooked. To address this, we propose Point-Approximate Matrix Multiplication (PAMM), a novel tensor compression technique that compresses the activations of the $Q,K,V$ projections in attention layers by a factor of up to $\times 512$, effectively erasing their memory footprint, while achieving similar or better final perplexity. PAMM is fully composable with efficient attention techniques such as FlashAttention, making it a practical and complementary method for memory-efficient LLM training.

Applications · Genetics, Cell Biology, Health, etc

Meital Bojan, Sanketh Vedula, Sai Advaith Maddipatla, Nadav Bojan Sellam, Anar Rzayev, Federico Napoli, Paul Schanda, Alexander Bronstein

The local structure of a protein strongly impacts its function and interactions with other molecules. Representing local biomolecular environments remains a key challenge while applying machine learning approaches over protein structures. The structural and chemical variability of these environments makes them challenging to model, and performing representation learning on these objects remains largely under-explored. In this work, we propose representations for local protein environments that leverage intermediate features from machine learning force fields (MLFFs). We extensively benchmark state-of-the-art MLFFs—comparing their performance across latent spaces and downstream tasks—and show that their embeddings capture local structural (e.g., secondary motifs) and chemical features (e.g., amino acid identity and protonation state), organizing protein environments into a structured manifold. We show that these representations enable zero-shot generalization and transfer across diverse downstream tasks. As a case study, we build a physics-informed, uncertainty-aware chemical shift predictor that achieves state-of-the-art accuracy in biomolecular NMR spectroscopy. Our results establish MLFFs as general-purpose, reusable representation learners for protein modeling, opening new directions in representation learning for structured physical systems.

Devvrit Khatri, Lovish Madaan, Rishabh Tiwari, Rachit Bansal, Venkata Sai Surya Subramanyam Duvvuri, Manzil Zaheer, Inderjit Dhillon, David Brandfonbrener, Rishabh Agarwal

Reinforcement learning (RL) has become central to training large language models (LLMs), yet the field lacks predictive scaling methodologies comparable to those established for pre-training. Despite rapidly rising compute budgets, there is no principled understanding of how to evaluate algorithmic improvements for scaling RL compute. We present the first large-scale systematic study, amounting to more than 400,000 GPU-hours, that defines a principled framework for analyzing and predicting RL scaling in LLMs. We fit sigmoidal compute-performance curves for RL training and ablate a wide range of common design choices to analyze their effects on asymptotic performance and compute efficiency. We observe: (1) Not all recipes yield similar asymptotic performance, Details such as loss aggregation, normalization, curriculum, and off-policy algorithm primarily modulate compute efficiency without materially shifting the asymptote, and (3) Stable, scalable recipes follow predictable scaling trajectories, enabling extrapolation from smaller-scale runs. Combining these insights, we propose a _best-practice_ recipe, ScaleRL, and demonstrate its effectiveness by successfully scaling and predicting validation performance on a single RL run scaled up to 100,000 GPU-hours. Our work provides both a _scientific framework_ for analyzing scaling in RL and a practical recipe that brings RL training closer to the predictability long achieved in pre-training.

Deep Learning · Everything Else

Tianyi Zhou, Deqing Fu, Mahdi Soltanolkotabi, Robin Jia, Vatsal Sharan

Language models treat numbers in the same way as ordinary word tokens, which introduces two major issues: (1) embeddings of numerical tokens primarily reflect their frequency in text corpora rather than their inherent numerical properties, leading to frequency bias, and (2) numbers are often split into multiple tokens, forcing the model to aggregate these pieces to recover their values. Inspired by the observation that pre-trained Large Language Models (LLMs) internally learn Fourier-like features for number tokens, we propose **Fo**urier **N**umber **E**mbedding **(FoNE)**, a novel method that directly maps numbers into the embedding space with their Fourier features. FoNE encodes each number as a single token with only two embedding dimensions per digit, effectively capturing numerical values without fragmentation. Compared to traditional subword and digit-wise embeddings, FoNE achieves higher accuracy on arithmetic tasks, requires significantly less training data, and offers more efficient training and inference. A $38$M-parameter Transformer trained from scratch with FoNE outperforms a fine-tuned Llama-3.2-1B model on addition, subtraction, and multiplication. FoNE is also the only method that achieves $100\\%$ accuracy on over 100,000 test examples across these tasks. On 6-digit decimal addition, FoNE needs 64$\times$ less data than subword and digit-wise embeddings to reach $\ge 99\\%$ accuracy, while using 3$\times$ and 6$\times$ fewer tokens per number, respectively.

Theory · Probabilistic Methods

Preetum Nakkiran, Arwen Bradley, Adam Golinski, Eugene Ndiaye, Michael Kirchhof, Sinead Williamson

Large Language Models (LLMs) often lack meaningful confidence estimates for the semantic content of their outputs. While base LLMs are known to exhibit next-token calibration, it remains unclear whether they can assess confidence in the actual meaning of their responses beyond the token level. We find that, when using a certain sampling-based notion of semantic calibration, base LLMs are remarkably well-calibrated: they can meaningfully assess confidence in various open-ended question-answering tasks, despite training only on next-token prediction. To formalize this phenomenon, we introduce "$B$-calibration," a notion of calibration parameterized by the choice of equivalence classes. Our main theoretical contribution establishes a mechanism for why semantic calibration emerges in base LLMs, leveraging a recent connection between calibration and local loss optimality. This theoretical mechanism leads to a testable prediction: base LLMs will be semantically calibrated when they can easily predict their own distribution over semantic answer classes before generating a response. We state three implications of this prediction, which we validate through experiments: (1) Base LLMs are semantically calibrated across question-answering tasks, (2) instruction-tuning procedures systematically break this calibration, and (3) chain-of-thought reasoning breaks calibration (intuitively because models cannot predict their final answers before completing their generation). To our knowledge, our work provides the first principled explanation of when and why semantic calibration emerges in LLMs.

General Machine Learning · Probabilistic Methods

Michael Kirchhof, Luca Füger, Adam Golinski, Eeshan Gunesh Dhekane, Arno Blaas, Seong Joon Oh, Sinead Williamson

The common approach to communicate a large language model's (LLM) uncertainty is to add a percentage number or a hedging word to its response. But is this all we can do? Instead of generating a single answer and then hedging it, an LLM that is fully transparent to the user needs to be able to reflect on its internal belief distribution and output a summary of all options it deems possible, and how likely they are. To test whether LLMs possess this capability, we develop the SelfReflect metric, an information-theoretic distance between a given summary and a distribution over answers. In interventional and human studies, we find that SelfReflect indicates even slight deviations, yielding a fine measure of faithfulness between a summary string and an LLM's actual internal distribution over answers. With SelfReflect, we make a resounding negative observation: modern LLMs are, across the board, incapable of revealing what they are uncertain about, neither through reasoning, nor chains-of-thoughts, nor explicit finetuning. However, we do find that LLMs are able to generate faithful summaries of their uncertainties if we help them by sampling multiple outputs and feeding them back into the context. This simple approach shines a light at the universal way of communicating LLM uncertainties whose future development the SelfReflect score enables. To support the development of this universal form of LLM uncertainties, we publish the code that implements our metric for arbitrary LLMs under https://github.com/apple/ml-selfreflect .

Applications · Time Series

Antanas Žilinskas, Robert Shorten, Jakub Marecek

Forecasting rare events in multivariate time-series data is a central challenge in machine learning, complicated by severe class imbalance, long-range dependencies, and distributional uncertainty. We introduce EVEREST, a transformer-based architecture for probabilistic rare-event forecasting that delivers calibrated predictions and tail-aware risk estimation, with auxiliary interpretability through attention-based signal attribution. EVEREST integrates four key components: (i) a learnable attention bottleneck for soft aggregation of temporal dynamics; (ii) an evidential head for estimating aleatoric and epistemic uncertainty via a Normal–Inverse–Gamma distribution; (iii) an extreme-value head that models tail risk using a Generalized Pareto Distribution; and (iv) a lightweight precursor head for early-event detection. These modules are jointly optimised with a composite loss combining focal loss, evidential negative log-likelihood, and a tail-sensitive EVT penalty, and act only at training time; deployment uses a single classification head with no inference overhead. We evaluate EVEREST on a real-world benchmark spanning a decade of space-weather data and demonstrate state-of-the-art performance, including True Skill Statistic (TSS) scores of 0.973, 0.970, and 0.966 at 24, 48, and 72-hour horizons for C-class flares. The model is compact (≈0.81M parameters), efficient to train on commodity hardware, and applicable to other high-stakes domains such as industrial monitoring, weather, and satellite diagnostics. Limitations include reliance on fixed-length inputs and exclusion of image-based modalities, motivating future extensions to streaming and multimodal forecasting.

Deep Learning · Attention Mechanisms

Maria-Luiza Vlǎdǎrean, Xuhui Zhang, Suvrit Sra

This paper studies the expressive power of linear attention layers for in-context learning (ICL) of linear dynamical systems (LDS). We consider training on sequences of inexact observations produced by noise-corrupted LDSs, with all perturbations being Gaussian. Importantly, this non-i.i.d. data setting is a significant step towards modeling real-world scenarios. We provide the optimal weight construction for a single linear-attention layer and show its equivalence to one step of Gradient Descent relative to an autoregression objective of window size one. Guided by experiments, we uncover a connection to a generalization of the Preconditioned Conjugate Gradient method for larger window sizes. We back our findings with numerical evidence. These results add to the existing understanding of transformers’ expressivity as in-context learners and offer plausible hypotheses for recent observations that place their performance on par with that of the Kalman Filter — the optimal model-dependent learner for this setting.

Applications · Language, Speech and Dialog

Ekaterina Fadeeva, Maiya Goloburda, Aleksandr Rubashevskii, Roman Vashurin, Artem Shelmanov, Preslav Nakov, Mrinmaya Sachan, Maxim Panov

Consistency-based methods have emerged as an effective approach to uncertainty quantification (UQ) in large language models. These methods typically rely on several generations obtained via multinomial sampling, measuring their agreement level. However, in short-form QA, multinomial sampling is prone to producing duplicates due to peaked distributions, and its stochasticity introduces considerable variance in uncertainty estimates across runs. We introduce a new family of methods that employ beam search to generate candidates for consistency-based UQ, yielding improved performance and reduced variance compared to multinomial sampling. We also provide a theoretical lower bound on the beam set probability mass under which beam search achieves a smaller error than multinomial sampling. We empirically evaluate our approach on six QA datasets and find that its consistent improvements over multinomial sampling lead to state-of-the-art UQ performance.

Applications · Language, Speech and Dialog

Kaiyang Wan, Lang Gao, Honglin Mu, Preslav Nakov, Yuxia Wang, Xiuying Chen

Multi-Hop Question Answering (MHQA) requires integrating dispersed, interdependent evidence through sequential reasoning under noise. This task is challenging for LLMs as they have a finite per-pass output capacity, beyond which the integration of task-relevant evidence proves unreliable. Consequently, the single-pass reasoning paradigm is inherently vulnerable to this capacity overflow. To formalize this bottleneck, our analysis establishes a Fano-style accuracy upper bound, defining a theoretical performance ceiling for single-pass LLMs. This bound reveals that accuracy inevitably collapses once task complexity exceeds model capacity, providing general principles for capacity-aware representation and structuring of MHQA in LLMs. Building on these principles, we introduce a proof-of-concept multi-call framework for MHQA, InfoQA. It ensures high per-step accuracy by combining capacity-aware task decomposition with active pruning of prior reasoning traces, keeping the information load within the single-pass limit. It further achieves robustness by a dependency-explicit workflow that enables precise control over the reasoning path. We construct a stringent and noise-rich benchmark to validate our theory and framework. Experimental results show that model behavior aligns with our predicted capacity curves while InfoQA achieves consistent performance improvements. We hope our work inspires more LLM multi-step reasoning methods: \faGithub \href{https://anonymous.4open.science/r/InfoQA-55D1}{InfoQA}.

General Machine Learning · Everything Else

Karen Ullrich, Jingtong Su, Claudia Shi, Arjun Subramonian, Amir Bar, Ivan Evtimov, Nikolaos Tsilivis, Randall Balestriero, Julia Kempe, Mark Ibrahim

Reliability is key to realizing the promise of autonomous UI-agents, multimodal agents that directly interact with the apps humans use, as users must be able to trust an agent to complete a given task. Current evaluations rely on fixed environments---often clones of existing apps--- which are limited in that they can only shed light on whether or how often an agent can complete a task within a specific environment. When deployed however, agents are likely to encounter variations in app design and content that can affect an agent’s ability to complete a task. To address this blind spot of measuring agent reliability across app variations, we develop OpenApps, a light-weight open-source ecosystem with six apps (messenger, calendar, maps, etc.) that are configurable in appearance and content. OpenApps requires just a single CPU to run, enabling easy generation and deployment of thousands of versions of each app. Specifically, we run more than 10,000 independent evaluations to study reliability across seven leading multimodal agents. We find that while standard reliability within a fixed app is relatively stable, reliability can vary drastically when measured across app variations. Task success rates for many agents can fluctuate by more than 50\% across app variations. For example, Kimi-VL-3B's average success across all tasks fluctuates from 63\% to just 4\% across app versions. We also find agent behaviors such as looping or hallucinating actions can differ drastically depending on the environment configuration. These initial findings highlight the importance of measuring reliability along this new dimension of app variations.

Applications · Physics

Weida Wang, Dongchen Huang, Jiatong LI, Tengchao Yang, Ziyang Zheng, Chuyi Peng, Di Zhang, Dong Han, Benteng Chen, Binzhao Luo 等

We introduce CMPhysBench, designed to assess the proficiency of Large Language Models (LLMs) in Condensed Matter Physics, as a novel Benchmark. CMPhysBench is composed of more than 520 graduate-level meticulously curated questions covering both representative subfields and foundational theoretical frameworks of condensed matter physics, such as magnetism, superconductivity, strongly correlated systems, etc. To ensure a deep understanding of the problem-solving process,we focus exclusively on calculation problems, requiring LLMs to independently generate comprehensive solutions. Meanwhile, leveraging tree-based representations of expressions, we introduce the Scalable Expression Edit Distance (SEED) score, which provides fine-grained (non-binary) partial credit and yields a more accurate assessment of similarity between prediction and ground-truth. Our results show that even the best models, Grok-4, reach only 36 average SEED score and 29% accuracy on CMPhysBench, underscoring a significant capability gap, especially for this practical and frontier domain relative to traditional physics.

Le-Trung Nguyen, Enzo Tartaglione, Van-Tam Nguyen

As AI increasingly shapes daily life, energy consumption and data privacy have become pressing concerns. On-device learning trains models directly on edge devices, cutting energy consumption and safeguarding data privacy. However, the expanding scale of modern neural networks creates a major obstacle for on-device training. Although prior work has concentrated on compact convolutional architectures, we instead apply subspace-based training to transformer models. Motivated by the idea that a model's essential information lies in a fixed subspace, we introduce Weight-Activation Subspace Iteration (WASI), a method that mitigates the memory bottleneck of backpropagation and boosts inference efficiency in transformer models by restricting training to this subspace. Our results demonstrate that WASI maintains accuracy comparable to vanilla training while reducing memory usage by up to $62\times$ and computational cost (FLOPs) by up to $2\times$. On a Raspberry Pi 5, WASI achieves roughly $1.4\times$ faster training and inference than vanilla training. The code is available at https://github.com/Le-TrungNguyen/ICLR2026-WASI.git.

Chenqi Li, Yu Liu, Timothy Denison, Tingting Zhu

Biosignals offer valuable insights into the physiological states of the human body. Although biosignal modalities differ in functionality, signal fidelity, sensor comfort, and cost, they are often intercorrelated, reflecting the holistic and interconnected nature of human physiology. This opens up the possibility of performing the same tasks using alternative biosignal modalities, thereby improving the accessibility, usability, and adaptability of health monitoring systems. However, the limited availability of large labeled datasets presents challenges for training models tailored to specific tasks and modalities of interest. Unsupervised cross-modal knowledge transfer offers a promising solution by leveraging knowledge from an existing modality to support model training for a new modality. Existing methods are typically based on knowledge distillation, which requires running a teacher model alongside student model training, resulting in high computational and memory overhead. This challenge is further exacerbated by the recent development of foundation models that demonstrate superior performance and generalization across tasks at the cost of large model sizes. To this end, we explore a new framework for unsupervised cross-modal knowledge transfer of biosignals by training a lightweight bridge network to align the intermediate representations and enable information flow between foundation models and across modalities. Specifically, we introduce an efficient strategy for selecting alignment positions where the bridge should be constructed, along with a flexible prototype network as the bridge architecture. Extensive experiments across multiple biosignal modalities, tasks, and datasets show that BioX-Bridge reduces the number of trainable parameters by 88-99\% while maintaining or even improving transfer performance compared to state-of-the-art methods.

General Machine Learning · Causality

Yewei Xia, Zhengming Chen, Haoyue Dai, Fuhong Wang, Yixin Ren, Yiqing Li, Kun Zhang, Shuigeng Zhou

Identifying latent variables and their induced causal structure is fundamental in various scientific fields. Existing approaches often rely on restrictive structural assumptions (e.g., purity assumption) and may become invalid when these assumptions are violated. We introduce Conditional Independent Component Analysis (CICA), a new principle that extracts components that are conditionally independent given latent variables. Under mild conditions, CICA can be optimized using a tractable proxy such as rank-deficiency constraints. Building on CICA, we establish an identifiability theory for linear non-Gaussian acyclic models with latent variables: solving CICA and then applying an appropriate row permutation to the sparsest CICA solution enables recovery of the causal structure. Accordingly, we propose an estimation method based on the identifiability theory and substantiate the algorithm with experiments on both synthetic and real-world datasets.