论文检索

Applications · Everything Else

Marcus Min, Yeqi Gao, Wilson Sy, Zhaoyu Li, Xujie Si, Osbert Bastani

Existing approaches to autoformalization---the task of translating informal mathematics into formal machine-verifiable languages---rely heavily on pre-defined libraries and expect LLMs to directly generate complete formalizations. These approaches face three fundamental limitations: they are bottlenecked by existing abstractions, they have difficulty handling the complexity of realistic statements, and they do not transfer well across formal languages. We propose $\textit{Divide and Abstract (DNA)}$, a zero-training framework that addresses these challenges through a two-phase approach. First, $\textit{DNA}$ extracts common mathematical concepts from the entire corpus and formalizes them as reusable abstractions, extending the target language's capability. Second, $\textit{DNA}$ hierarchically decomposes new statements into structured informal clauses, translates each clause using the learned abstractions, and composes them into complete formalizations. Our evaluation on the LeanEuclidPlus and ProofNet-Hard benchmarks demonstrates consistent improvements across multiple model families, achieving up to $\textbf{8.6}\times$ performance gains over baselines. Notably, $\textit{DNA}$ enables smaller models to match baselines using much larger models, and shows particularly strong performance on complex mathematical statements requiring nested reasoning. Furthermore, our framework requires no training on target languages, making it effective for low-resource domain-specific languages. Our code is available at https://github.com/marcusm117/DNA.

Social Aspects · Trustworthy Machine Learning

Efstratios Zaradoukas, Bardh Prenkaj, Gjergji Kasneci

During pretraining, LLMs inadvertently memorize sensitive or copyrighted data, posing significant compliance challenges under legal frameworks like the GDPR and the EU AI Act. Fulfilling these mandates demands techniques that can remove information from a deployed model without retraining from scratch. Existing unlearning approaches attempt to address this need, but often leak the very data they aim to erase, sacrifice fluency and robustness, or depend on costly external reward models. We introduce PURGE (Policy Unlearning through Relative Group Erasure), a novel method grounded in the Group Relative Policy Optimization framework that formulates unlearning as a verifiable problem. PURGE uses an intrinsic reward signal that penalizes any mention of forbidden concepts, allowing safe and consistent unlearning. Our approach achieves up to $\times$46 lower token usage per target than state-of-the-art methods, while improving fluency by +5.48\% and adversarial robustness by +12.02\% over the base model. Extensive evaluation on the Real World Knowledge Unlearning (RWKU) benchmark shows that PURGE reaches 11\% unlearning effectiveness while preserving 98\% of original utility. PURGE shows that framing LLM unlearning as a verifiable task, enables more reliable, efficient, and scalable forgetting, suggesting a promising new direction for unlearning research that combines theoretical guarantees, improved safety, and practical deployment efficiency.

Deep Learning · Algorithms

Nikhil Shivakumar Nayak, Krishnateja Killamsetty, Ligong Han, Abhishek Bhandwaldar, Prateek Chanda, Kai Xu, Oleg Silkin, Mustafa Eyceoz, Hao Wang, Aldo Pareja 等

Continual learning in large language models (LLMs) is prone to catastrophic forgetting, where adapting to new tasks significantly degrades performance on previously learned ones. Existing parameter-efficient methods often limit model expressivity or introduce new parameters per task, creating scalability issues. To address these limitations, we introduce **Orthogonal Subspace Fine-Tuning (OSFT)**, a novel parameter-efficient approach for continual learning. OSFT leverages adaptive singular value decomposition (SVD) to dynamically identify and preserve critical, high-rank parameter subspaces that encode prior knowledge. All updates for new tasks are constrained to be strictly orthogonal to these preserved subspaces, which minimizes interference while maintaining a fixed parameter count and avoiding the need to store task-specific gradients. We extensively evaluate OSFT on standard continual learning benchmarks using both encoder-decoder (T5-Large) and decoder-only (LLaMA-2 7B, Mistral-7B) models across diverse tasks. Empirically, our method achieves a state-of-the-art trade-off between learnability and knowledge retention, dominating the Pareto frontier, with **up to 7\% higher** average accuracy than recent baselines like O-LoRA, and **reduces forgetting to near-negligible levels**. It notably maintains the model's general linguistic capabilities, instruction-following, and safety throughout the learning process. OSFT provides a practical, theoretically grounded, and scalable solution that effectively balances model plasticity and knowledge retention for continual learning in LLMs. Code is available at https://github.com/Red-Hat-AI-Innovation-Team/mini_trainer.

Applications · Robotics

Yash Jangir, Yidi Zhang, Kashu Yamazaki, Chenyu Zhang, Kuan-Hsun Tu, Tsung-Wei Ke, Lei Ke, Yonatan Bisk, Katerina Fragkiadaki

The pursuit of robot generalists, instructable agents capable of performing diverse tasks across diverse environments, demands rigorous and scalable evaluation. Yet real-world testing of robot policies remains fundamentally constrained: it is labor-intensive, slow, unsafe at scale, and difficult to reproduce. As policies expand in scope and complexity, these barriers only intensify, since defining ``success'' in robotics often hinges on nuanced human judgments of execution quality. We introduce RobotArenaInf, a new benchmarking framework that overcomes these challenges by shifting VLA evaluation into large-scale simulated environments augmented with online human feedback. Leveraging advances in vision-language models, 2D-to-3D generative modeling, and differentiable rendering, our approach automatically converts video demonstrations from widely used robot datasets into simulated counterparts. Within these digital twins, we assess VLA policies using both automated VLM-guided scoring and scalable human preference judgments collected from crowdworkers, transforming human involvement from tedious scene setup, resetting, and safety supervision into lightweight preference comparisons. To measure robustness, we systematically perturb simulated environments along multiple axes, including textures and object placements, stress-testing policy generalization under controlled variation. The result is a continuously evolving, reproducible, and scalable benchmark for real-world-trained robot manipulation policies, addressing a critical missing capability in today’s robotics landscape. Benchmark website at \href{https://robotarenainf.github.io}{\texttt{robotarenainf.github.io}}.

Qiushi Sun, Jingyang Gong, Yang Liu, Qiaosheng Chen, Lei Li, Kai Chen, Qipeng Guo, Ben Kao, Fei Yuan

The scope of neural code intelligence is rapidly expanding beyond text-based source code to encompass the rich visual outputs that programs generate. This visual dimension is critical for advanced applications like flexible content generation and precise, program-driven editing of visualizations. However, progress has been impeded by the scarcity of high-quality multimodal code data, a bottleneck stemming from challenges in synthesis and quality assessment. To address these challenges, we make contributions from both a data and modeling perspective. We first introduce a complete synthesis toolkit that leverages reciprocal synergies between data modalities to efficiently produce a large-scale, high-quality corpus spanning from standard charts to complex interactive web UIs and code-driven animations. Leveraging this toolkit, we construct JanusCode-800K, the largest multimodal code corpus to date. This powers the training of our models, JanusCoder and JanusCoderV, which establish a visual-programmatic interface for generating code from textual instructions, visual inputs, or a combination of both. Our unified model is a departure from existing approaches that build specialized models for isolated tasks. Extensive experiments on both text-centric and vision-centric coding tasks demonstrate the superior performance of the JanusCoder series, with our 7B to 14B scale models approaching or even exceeding the performance of commercial models. Furthermore, extensive analysis provides key insights into harmonizing programmatic logic with its visual expression. Our code and checkpoints are available at \url{https://github.com/InternLM/JanusCoder}.

Applications · Health

Zongliang Ji, Yifei Sun, Andre Amaral, Anna Goldenberg, Rahul G. Krishnan

Deploying clinical ML is slow and brittle: models that work at one hospital often degrade under distribution shifts at the next. In this work, we study a simple question -- can large language models (LLMs) create portable patient embeddings i.e. representations of patients enable a downstream predictor built on one hospital to be used elsewhere with minimal-to-no retraining and fine-tuning. To do so, we map from irregular ICU time series onto concise natural language summaries using a frozen LLM, then embed each summary with a frozen text embedding model to obtain a fixed length vector capable of serving as input to a variety of downstream predictors. Across three cohorts (MIMIC-IV, HIRID, PPICU), on multiple clinically grounded forecasting and classification tasks, we find that our approach is simple, easy to use and competitive with in-distribution with grid imputation, self-supervised representation learning, and time series foundation models, while exhibiting smaller relative performance drops when transferring to new hospitals. We study the variation in performance across prompt design, with structured prompts being crucial to reducing the variance of the predictive models without altering mean accuracy. We find that using these portable representations improves few-shot learning and does not increase demographic recoverability of age or sex relative to baselines, suggesting little additional privacy risk. Our work points to the potential that LLMs hold as tools to enable the scalable deployment of production grade predictive models by reducing the engineering overhead.

Theory · Optimization

Jinrui Huang, Xueqin Wang, Dong Liu, Jingguo Lan, Runxiong Wu

This paper focuses on decentralized composite optimization over networks without a central coordinator. We propose a novel decentralized Symmetric ADMM algorithm that incorporates multiple communication rounds within each iteration, derived from a new constraint formulation that enables information exchange beyond immediate neighbors. While increasing per-iteration communication, our approach significantly reduces the total number of iterations and overall communication cost. We further design optimal communication rules that minimize the number of rounds and variables transmitted per iteration. The proposed algorithms are shown to achieve linear convergence under standard assumptions. Extensive experiments on regression and classification tasks validate the theoretical results and demonstrate superior performance compared to existing decentralized optimization methods.

Deep Learning · Everything Else

Francesco Caso, Samuele Fonio, Simone Monaco, Nicola Saccomanno, Fabrizio Silvestri

Neural networks implicitly learn class-specific functional modules. In this work, we ask: Can such modules be isolated and recombined? We introduce a method for training sparse networks that accurately classify only a designated subset of classes while remaining deliberately uncertain on all others, functioning as class-specific subnetworks. A novel KL-divergence-based loss trains only the functional module for the assigned set, and an iterative magnitude pruning procedure removes irrelevant weights. Across multiple datasets (MNIST, FMNIST, CIFAR-10, CIFAR-100, tabular and text classification data) and architectures (MLPs, CNNs, ResNet, VGG), we show that these subnetworks achieve high accuracy on their target classes with minimal leakage to others. When combined via weight summation or logit averaging, these specialized subnetworks act as functional modules of a composite model that often recovers generalist performance. For simpler models and datasets, we experimentally confirm that the resulting modules are mode-connected, which justifies summing their weights. Our approach offers a new pathway toward building modular, composable deep networks with interpretable functional structure.

Optimization · Zero-order and Black-box Optimization

Yimeng Zeng, Natalie Maus, Haydn Jones, Jeffrey Tao, Fangping Wan, Marcelo Der Torossian Torres, Cesar de la Fuente, Ryan Marcus, Osbert Bastani, Jacob Gardner

In multi-task Bayesian optimization, the goal is to leverage experience from optimizing existing tasks to improve the efficiency of optimizing new ones. While approaches using multi-task Gaussian processes or deep kernel transfer exist, the performance improvement is marginal when scaling beyond a moderate number of tasks. We introduce **BOLT**, an initialization-only transfer strategy that distills prior BO runs into an LLM which proposes candidates for new tasks, while the surrogate at test time remains single-task. The LLM is periodically fine-tuned on top solutions from completed runs, creating a closed loop where better BO outputs yield better initializations over time. This decoupled design scales to roughly 1500 tasks without the saturation observed for shared-surrogate MTBO and adds only a small, amortized overhead relative to the BO inner loops. We evaluate on two domains: database query optimization and antimicrobial peptide design. We demonstrate that LLM-generated initializations steadily improve and accelerate BO, and with sufficient fine-tuning, a few LLM samples often match or surpass full ''from-scratch'' BO with far fewer oracle calls.

Applications · Language, Speech and Dialog

Bang Xiao, Lingjie Jiang, Shaohan Huang, Tengchao Lv, Yupan Huang, xun wu, Lei Cui, Furu Wei

Large Language Models (LLMs) have become valuable assistants for developers in code-related tasks. While LLMs excel at traditional programming tasks such as code generation and bug fixing, they struggle with visually-oriented coding tasks, often producing suboptimal aesthetics. In this paper, we introduce a new pipeline to enhance the aesthetic quality of LLM-generated code. We first construct AesCode-358K, a large-scale instruction-tuning dataset focused on code aesthetics. Next, we propose agentic reward feedback, a multi-agent system that evaluates executability, static aesthetics, and interactive aesthetics. Building on this, we develop GRPO-AR, which integrates these signals into the GRPO algorithm for joint optimization of functionality and code aesthetics. Finally, we develop OpenDesign, a benchmark for assessing code aesthetics. Experimental results show that combining supervised fine-tuning on AesCode-358K with reinforcement learning using agentic reward feedback significantly improves performance on OpenDesign and enhances results on existing benchmarks such as PandasPlotBench. Notably, our AesCoder-4B surpasses GPT-4o and GPT-4.1, and achieves performance comparable to large open-source models with 480B–685B parameters, underscoring the effectiveness of our approach.

Applications · Climate

Sumanth Varambally, Marshall Fisher, Jas Thakker, Yiwei Chen, Zhirui Xia, Yasaman Jafari, Ruijia Niu, Manas Jain, Veeramakali Vignesh Manivannan, Zachary Novack 等

Foundation models for weather science are pre-trained on vast amounts of structured numerical data and outperform traditional weather forecasting systems. However, these models lack language-based reasoning capabilities, limiting their utility in interactive scientific workflows. Large language models (LLMs) excel at understanding and generating text but cannot reason about high-dimensional meteorological datasets. We bridge this gap by building the first agentic framework for weather science. Our framework includes a Python code-based environment for agents (ZephyrusWorld) to interact with weather data, featuring tools including a WeatherBench 2 dataset indexer, geolocator for geocoding from natural language, weather forecasting, climate simulation capabilities, and a climatology module for querying precomputed climatological statistics (e.g., means, extremes, and quantiles) across multiple timescales. We design Zephyrus, a multi-turn LLM-based weather agent that iteratively analyzes weather datasets, observes results, and refines its approach through conversational feedback loops. We accompany the agent with a new benchmark, ZephyrusBench, with a scalable data generation pipeline that constructs diverse question-answer pairs across weather-related tasks, from basic lookups to advanced forecasting, extreme event detection, and counterfactual reasoning. Experiments on this benchmark demonstrate the strong performance of Zephyrus agents over text-only baselines, outperforming them by up to 44 percentage points in correctness. However, the hard tasks are still difficult even with frontier LLMs, highlighting the challenging nature of our benchmark and suggesting room for future development. Our codebase and benchmark are available at \url{https://github.com/Rose-STL-Lab/Zephyrus}.

General Machine Learning · Causality

Matthew Vowels, Mathieu Rochat, Sina Akbari

Artificial Neural Networks (ANNs), including fully-connected networks and transformers, are highly flexible and powerful function approximators, widely applied in fields like computer vision and natural language processing. However, their inability to inherently respect causal structures can limit their robustness, making them vulnerable to covariate shift and difficult to interpret/explain. This poses significant challenges for their reliability in real-world applications. In this paper, we introduce Causal Transformers (CaTs), a general model class designed to operate under predefined causal constraints, as specified by a Directed Acyclic Graph (DAG). CaTs retain the powerful function approximation abilities of traditional neural networks while adhering to the underlying structural constraints, improving robustness, reliability, and interpretability at inference time. This approach opens new avenues for deploying neural networks in more demanding, real-world scenarios where robustness and explainability is critical.

Social Aspects · Trustworthy Machine Learning

Min-Hsuan Yeh, Max Kamachee, Seongheon Park, Sharon Li

To mitigate the impact of hallucination nature of LLMs, many studies propose detecting hallucinated generation through uncertainty estimation. However, these approaches predominantly operate at the sentence or paragraph level, failing to pinpoint specific spans or entities responsible for hallucinated content. This lack of granularity is especially problematic for long-form outputs that mix accurate and fabricated information. To address this limitation, we explore entity-level hallucination detection. We propose a new data set, HalluEntity, which annotates hallucination at the entity level. Based on the dataset, we comprehensively evaluate uncertainty-based hallucination detection approaches across 17 modern LLMs. Our experimental results show that uncertainty estimation approaches focusing on individual token probabilities tend to over-predict hallucinations, while context-aware methods show better but still suboptimal performance. Through an in-depth qualitative study, we identify relationships between hallucination tendencies and linguistic properties and highlight important directions for future research. HalluEntity: https://huggingface.co/datasets/samuelyeh/HalluEntity

Deep Learning · Everything Else

Xiaoyuan Liu, Tian Liang, Dongyang Ma, Deyu Zhou, Haitao Mi, Pinjia He, Yan Wang

In the world of Harry Potter, when Dumbledore's mind is overburdened, he extracts memories into a Pensieve to be revisited later. In the world of AI, while we possess the Pensieve—mature databases and retrieval systems, our models inexplicably lack the ``wand'' to operate it. They remain like a Dumbledore without agency, passively accepting a manually engineered context as their entire memory. This work finally places the wand in the model's hand. We introduce StateLM, a new class of foundation models endowed with an internal reasoning loop to manage their own state. We equip our model with a suite of memory tools, such as context pruning, document indexing, and note-taking, and train it to actively manage these tools. By learning to dynamically engineering its own context, our model breaks free from the architectural prison of a fixed window. Experiments across various model sizes demonstrate StateLM's effectiveness across diverse scenarios. On long-document QA tasks, StateLMs consistently outperform standard LLMs across all model scales; on the chat memory task, they achieve absolute accuracy improvements of 10% to 20% over standard LLMs. On the deep research task BrowseComp-Plus, the performance gap becomes even more pronounced: StateLM achieves up to 52% accuracy, whereas standard LLM counterparts struggle around 5%. Ultimately, our approach shifts LLMs from passive predictors to state-aware agents where reasoning becomes a stateful and manageable process.

Deep Learning · Generative Models and Autoencoders

Todd Nief, David Reber, Sean Richardson, Ari Holtzman

When an LLM learns a new fact during finetuning (e.g., new movie releases, newly elected pope, etc.), where does this information go? Are entities enriched with relation information immediately, or do models recall information just-in-time before a prediction? Or, are "all of the above" true, with LLMs implementing multiple redundant heuristics? Existing localization approaches (e.g., activation patching) are ill-suited for this analysis because they usually replace parts of the residual stream, thus overriding previous information. To fill this interpretability gap, we propose dynamic weight grafting, an analysis technique that selectively grafts subsets of weights from a finetuned model onto a pretrained model. Using this technique, we show two separate pathways for retrieving finetuned relation information: 1) "enriching" the residual stream with relation information while processing the tokens that correspond to an entity (e.g., "Zendaya" in "Zendaya co-starred with Timothée Chalamet" and 2) "recalling" this information at the final token position before generating a target fact. In some cases, models need information from both of these pathways to correctly generate finetuned facts while, in other cases, either the "enrichment" or "recall" pathway alone is sufficient. We localize the "recall" pathway to model components---finding that "recall" occurs via both task-specific attention mechanisms and an entity-specific extraction step in the feedforward networks of the final layers before prediction. By targeting model components and parameters, as opposed to just activations, we are able to understand the mechanisms by which finetuned knowledge is retrieved during generation.

Reinforcement Learning · Multi-agent

Junpei Komiyama, Daisuke Oba, Masafumi Oyamada

We study best-of-$N$ for large language models (LLMs) where the selection is based on majority voting. In particular, we analyze the limit $N \to \infty$, which we denote as best-of-$\infty$. While this approach achieves impressive performance in the limit, it requires an infinite test-time budget. To address this, we propose an adaptive generation scheme that selects $N$ based on answer agreement, thereby efficiently allocating inference-time computation. Beyond adaptivity, we extend the framework to weighted ensembles of multiple LLMs, showing that such mixtures can outperform any individual model. The optimal ensemble weighting is formulated and efficiently computed as a mixed-integer linear program. Extensive experiments demonstrate the effectiveness of our approach. Our code is available at https://github.com/jkomiyama/BoInf-code-publish/.

General Machine Learning · Transfer, Multitask and Meta-learning

Hongye Xu, Bartosz Krawczyk

Continual learning (CL) seeks models that acquire new skills without erasing prior knowledge. In exemplar-free class-incremental learning (EFCIL), this challenge is amplified because past data cannot be stored, making representation drift for old classes particularly harmful. Prototype-based EFCIL is attractive for its efficiency, yet prototypes drift as the embedding space evolves; thus, projection-based drift compensation has become a popular remedy. We show, however, that existing one-directional projections introduce systematic bias: they either retroactively distort the current feature geometry or align past classes only locally, leaving cycle inconsistencies that accumulate across tasks. We introduce bidirectional projector alignment during training: two maps, old$\to$new and new$\to$old, are trained during each new task with stop-gradient gating and a cycle-consistency objective so that transport and representation co-evolve. Analytically, we prove that the cycle loss contracts the singular spectrum toward unity in whitened space and that improved transport of class means/covariances yields smaller perturbations of classification log-odds, preserving old-class decisions and directly mitigating catastrophic forgetting. Empirically, across standard EFCIL benchmarks, our method achieves unprecedented reductions in forgetting while maintaining very high accuracy on new tasks, consistently outperforming state-of-the-art approaches. The code is available at https://github.com/HXuSz11/BiCyc_ICLR2026.

Applications · Chemistry and Drug Discovery

Jungseob Yi, Seoyoung Choi, Sun Kim, Sangseon Lee

Virtual screening (VS) aims to identify bioactive compounds from vast chemical libraries, but remains difficult in low-label regimes where only a few actives are known. Existing methods largely rely on general-purpose molecular fingerprints and overlook class-discriminative substructures critical to bioactivity. Moreover, they consider molecules independently, limiting effectiveness in low-label regimes. We introduce SubDyve, a network-based VS framework that constructs a subgraph-aware similarity network and propagates activity signals from a small known actives. When few active compounds are available, SubDyve performs iterative seed refinement, incrementally promoting new candidates based on local false discovery rate. This strategy expands the seed set with promising candidates while controlling false positives from topological bias and overexpansion. We evaluate SubDyve on ten DUD-E targets under zero-shot conditions and on the CDK7 target with a 10-million-compound ZINC dataset. SubDyve consistently outperforms existing fingerprint or embedding-based approaches, achieving margins of up to +34.0 on the BEDROC and +24.6 on the $EF_{1\\%}$ metric.

Theory · Optimization

Sammy Khalife, Andrea Lodi

In the recent years, branch-and-cut algorithms have been the target of data-driven approaches designed to enhance the decision making in different phases of the algorithm such as branching, or the choice of cutting planes (cuts). In particular, for cutting plane selection two score functions have been proposed in the literature to evaluate the quality of a cut: branch-and-cut tree size and gap closed. In this paper, we present new sample complexity lower bounds, valid for both scores. We show that for a wide family of classes $\mathcal{F}$ that maps an instance to a cut, learning over an unknown distribution of the instances to minimize those scores requires at least (up to multiplicative constants) as many samples as learning from the same class function $\mathcal{F}$ any generic target function (using square loss). Our results also extend to the case of learning from a restricted set of cuts, namely those from the Simplex tableau. To the best of our knowledge, these constitute the first lower bounds for the learning-to-cut framework. We compare our bounds to known upper bounds in the case of neural networks and show they are nearly tight, suggesting that both scores (gap closed and tree size) are of comparable difficulty from a learning standpoint. Guided by this insight, we provide empirical evidence -- by using a graph neural network cut selection evaluated on various integer programming problems -- that gap closed is a practical and effective proxy for minimizing the tree size. Although the gap closed score has been extensively used in the integer programming literature, this is the first principled analysis discussing both scores simultaneously both theoretically and computationally.

General Machine Learning · Everything Else

Nina Mishra, Yonatan Naamad, Tal Wagner, Lichen Zhang

Approximate nearest neighbor search (ANN) is a common way to retrieve relevant search results, especially now in the context of large language models and retrieval augmented generation. One of the most widely used algorithms for ANN is based on constructing a multi-layer graph over the dataset, called the Hierarchical Navigable Small World (HNSW). While this algorithm supports insertion of new data, it does not support deletion of existing data. Moreover, deletion algorithms described by prior work come at the cost of increased query latency, decreased recall, or prolonged deletion time. In this paper, we propose a new theoretical framework for graph-based ANN based on random walks. We then utilize this framework to analyze a randomized deletion approach that preserves hitting time statistics compared to the graph before deleting the point. We then turn this theoretical framework into a \emph{deterministic} deletion algorithm, and show that it provides better tradeoff between query latency, recall, deletion time, and memory usage through an extensive collection of experiments.