ICLR 2026 论文列表

Natural language interfaces for vehicle control must contend with vague commands, evolving dialogue context, and strict protocol constraints. We introduce ClarifyVC, a unified framework that integrates a hybrid data-augmentation pipeline (ClarifyVC-Data), reference models trained on the data (ClarifyVC-Models) and a evaluation protocol (ClarifyVC-Eval). The agent-orchestrated pipeline generates diverse, ambiguity-rich dialogues from real-world seeded queries under schema and safety constraints, while the evaluation protocol systematically probes single-turn parsing, conservative clarification under extreme fuzziness, and multi-turn grounding. Fine-tuning on ClarifyVC-Data yields consistent gains—up to 15\% higher parsing accuracy, 20\% stronger ambiguity resolution, and 98\% protocol compliance—across realistic in-cabin scenarios, with human-in-the-loop assessments confirming high realism, coherence, and applicability. ClarifyVC thus advances beyond simulation-only datasets by tightly coupling real-world grounding with scalable generation and standardized evaluation, and provides a generalizable pipeline for broader interactive control domains.

The ability of AI to sense and identify various substances based on their smell alone can have profound impacts on allergen detection (e.g., smelling gluten or peanuts in a cake), monitoring the manufacturing process, and sensing hormones that indicate emotional states, stress levels, and diseases. Despite these broad impacts, there are virtually no large-scale benchmarks, and therefore little progress, for training and evaluating AI systems’ ability to smell in the real world. In this paper, we use portable gas and chemical sensors to create SMELLNET, the first large-scale database that digitizes a diverse range of smells in the natural world. SMELLNET contains about 828,000 data points across 50 substances, spanning nuts, spices, herbs, fruits, and vegetables, and 43 mixtures among them, with 68 hours of data collected. Using SMELLNET, we developed SCENTFORMER, a Transformer-based architecture combining temporal differencing and sliding-window augmentation for smell data. For the SMELLNET-BASE classification task, SCENTFORMER achieves 58.5% Top-1 accuracy, and for the SMELLNET-MIXTURE distribution prediction task, SCENTFORMER achieves 50.2% Top-1@0.1 on the test-seen split. SCENTFORMER’s ability to generalize across conditions and capture transient chemical dynamics demonstrates the promise of temporal modeling in olfactory AI. SMELLNET and SCENTFORMER lay the groundwork for real-world olfactory applications across healthcare, food and beverage, environmental monitoring, manufacturing, and entertainment.

Large language models are trained on massive corpora of web data, which may include private data, copyrighted material, factually inaccurate data, or data that degrades model performance. Eliminating the influence of such problematic datapoints on a model through complete retraining---by repeatedly pretraining the model on datasets that exclude these specific instances---is computationally prohibitive. To address this, unlearning algorithms have been proposed, that aim to eliminate the influence of particular datapoints at a low computational cost, while leaving the rest of the model intact. However, precisely unlearning the influence of data on a large language model has proven to be a major challenge. In this work, we propose a new algorithm, MSA (**M**odel **S**tate **A**rithmetic), for unlearning datapoints in large language models. MSA utilizes prior model checkpoints--- artifacts that record model states at different stages of pretraining--- to estimate and counteract the effect of targeted datapoints. Our experimental results show that MSA achieves competitive performance and often outperforms existing machine unlearning algorithms across multiple benchmarks, models, and evaluation metrics, suggesting that MSA could be an effective approach towards more flexible large language models that are capable of data erasure.

Large language models (LLMs) can be prompted with specific styles (e.g., formatting responses as lists), including in malicious queries. Prior jailbreak research mainly augments these queries with additional string transformations to maximize attack success rate (ASR). However, the impact of style patterns in the original queries that are semantically irrelevant to the malicious intent remains unclear. In this work, we seek to understand whether style patterns compromise LLM safety, how superficial style alignment increases model vulnerability, and how best to mitigate these risks during alignment. We first define ASR inflation as the increase in ASR due to style patterns in existing jailbreak benchmark queries. By evaluating $32$ LLMs across seven benchmarks, we find that nearly all models exhibit ASR inflation. Notably, the inflation correlates with an LLM's relative attention to style patterns, which also overlap more with its instruction-tuning data when inflation occurs. We then investigate superficial style alignment, and find that fine-tuning with specific styles makes LLMs more vulnerable to jailbreaks of those same styles. Finally, we propose SafeStyle, a defense strategy that incorporates a small amount of safety training data augmented to match the distribution of style patterns in the fine-tuning data. Across three LLMs, six fine-tuning style settings, and two real-world instruction-tuning datasets, SafeStyle consistently outperforms baselines in maintaining LLM safety.

AI agents may soon become capable of autonomously completing valuable, long-horizon tasks in diverse domains. Current benchmarks either do not measure real-world tasks, or are not sufficiently difficult to meaningfully measure frontier models. To this end, we present Terminal-Bench 1.5: a carefully curated hard benchmark composed of 74 tasks in computer terminal environments inspired by problems from real workflows. Each task features a unique environment, human-written solution, and comprehensive tests for verification. We show that frontier models and agents score less than 50% on the benchmark and conduct an error analysis to identify areas for model and agent improvement. We publish the dataset and evaluation harness to assist developers and researchers in future work.

Story generation aims to automatically produce coherent, structured, and engaging narratives. Although large language models (LLMs) have significantly advanced text generation, stories generated by LLMs still diverge from human-authored works regarding complex narrative structure and human-aligned preferences. A key reason is the absence of effective modeling of human story preferences, which are inherently subjective and under-explored. In this work, we systematically evaluate the modeling of human story preferences and introduce StoryRMB, the first benchmark for assessing reward models on story preferences. StoryRMB contains $1,133$ high-quality, human-verified instances, each consisting of a prompt, one chosen story, and three rejected stories. We find existing reward models struggle to select human-preferred stories, with the best model achieving only $66.3\%$ accuracy. To address this limitation, we construct roughly $100,000$ high-quality story preference pairs across diverse domains and develop StoryReward, an advanced reward model for story preference trained on this dataset. StoryReward achieves state-of-the-art (SoTA) performance on StoryRMB, outperforming much larger models. We also adopt StoryReward in downstream test-time scaling applications for best-of-n (BoN) story selection and find that it generally chooses stories better aligned with human preferences. We will release our dataset, model, and code to facilitate future research.

In recent months, large language models (LLMs) have made significant progress in mathematical proof generation, but further advancement is hindered by the lack of a large-scale, high-quality dataset of human-evaluated proofs. While expensive to create, such a dataset is essential for driving improvements in training and addressing key open questions in the field of automated proof generation. Specifically, it remains unknown (1) how large the gap is between natural language and formal proof generation, (2) how final-answer accuracy relates to full proof correctness, and (3) how best-of-n selection strategies can affect proof quality. In this work, we present the Open Proof Corpus (OPC), a dataset comprising over 5,000 human-evaluated proofs produced by state-of-the-art LLMs. The OPC was specifically designed for broad applicability and downstream usage in proof generation research and is the first large dataset of LLM-generated solutions to problems from prestigious mathematics competitions such as the USAMO and IMO. Using the OPC, we address the open questions outlined above and provide new insights into LLMs' strengths and limitations in mathematical reasoning. Finally, to showcase the utility of the OPC, we finetune an 8B-parameter model on the dataset, obtaining a model that matches Gemini-2.5-Pro, and performs close to the best model, GPT-5, on evaluating proof correctness.

Dynamic data pruning accelerates training by focusing on informative samples. However, comparing importance scores across different model states introduces inconsistency (score context drift), and variable selection rates bias gradient dynamics over time (temporal gradient bias). We introduce RePB (Resolving Pruning Biases), a framework addressing these issues. RePB performs pruning decisions within local windows (short sequences of batches) during training, using loss scores computed with a near-constant model state within each window to ensure valid comparisons. These decisions determine the data subset used in the subsequent training phase. To counteract temporal gradient bias arising from non-uniform sample inclusion, cumulative temporal rescaling reweights sample losses during training based on their historical selection frequency. We provide theoretical grounding for RePB's consistency in score comparison and gradient alignment. Experiments show RePB achieves near-full-dataset accuracy using reduced data (most above 30%) across 16 datasets, 17 models and 13 tasks, offering a robust and scalable approach to efficient deep learning.

Mixture-of-Experts (MoE) architectures have become the key to scaling modern LLMs, yet little is understood about how their sparse routing dynamics respond to multilingual data. In this work, we analyze expert routing patterns using parallel multilingual datasets and present highly interpretable layer-wise phenomena. We find that MoE models route tokens in language-specific ways in the early and late decoder layers but exhibit significant cross-lingual routing alignment in middle layers, mirroring parameter-sharing trends observed in dense LLMs. In particular, we reveal a clear, strong correlation between a model's performance in a given language and how similarly its tokens are routed to English in these layers. Extending beyond correlation, we explore inference-time interventions that induce higher cross-lingual routing alignment. We introduce a method that steers the router by promoting middle-layer task experts frequently activated in English, and it successfully increases multilingual performance. These 1-2% gains are remarkably consistent across two evaluation tasks, three models, and 15+ languages, especially given that these simple interventions override routers of extensively trained, state-of-the-art LLMs. In comparison, interventions outside of the middle layers or targeting multilingual-specialized experts only yield performance degradation. Altogether, we present numerous findings that explain how MoEs process non-English text and demonstrate that generalization is limited by the model’s ability to leverage language-universal experts in all languages.

Continual Learning (CL) requires a model to learn multiple tasks in sequence while maintaining both stability—preserving knowledge from previously learned tasks, and plasticity—effectively learning new tasks. Orthogonal projection has emerged as an effective and popular paradigm in CL, where it partitions the gradient space of previously learned tasks into two orthogonal subspaces: a primary subspace and a minor subspace. New tasks are learned effectively within the minor subspace, thereby reducing interference with previously acquired knowledge. However, existing orthogonal projection methods struggle to achieve an optimal balance between plasticity and stability, as it is hard to appropriately partition the gradient space. In this work, we consider a continual learning paradigm based on Low-Rank Adaptation (LoRA), which has gained considerable attention due to its efficiency and wide applicability, and propose a novel approach for continual learning, called SplitLoRA. We first provide a theoretical analysis of how subspace partitioning affects model stability and plasticity. Informed by this analysis, we then introduce an effective method that derives the optimal partition of the gradient space for previously learned tasks. This approach effectively balances stability and plasticity in continual learning. Experimental results on multiple datasets demonstrate that the proposed method achieves state-of-the-art performance. The code is available at https://anonymous.4open.science/r/SplitLoRA-FB45.

Attention learners, neural networks built on the attention mechanism, e.g., transformers, excel at learning the implicit relationships that relate sequences to their corresponding properties, e.g., mapping a given sequence of tokens to the probability of the next token. However, the learning process tends to be costly. To address this, we present a novel paradigm named **Atte**ntion **N**eural **T**eaching (AtteNT) that reinterprets the learning process through a nonparametric teaching perspective. Specifically, the latter provides a theoretical framework for teaching mappings that are implicitly defined (i.e., nonparametric) via example selection. Such an implicit mapping is embodied through a dense set of sequence-property pairs, with the AtteNT teacher selecting a subset to accelerate convergence in attention learner training. By analytically investigating the role of attention on parameter-based gradient descent during training, and recasting the evolution of attention learners, shaped by parameter updates, through functional gradient descent in nonparametric teaching, we show *for the first time* that teaching attention learners is consistent with teaching importance-adaptive nonparametric learners. These new findings readily commit AtteNT to enhancing learning efficiency of attention learners. Specifically, we observe training time reductions of 13.01% for LLMs and 20.58% for ViTs, spanning both fine-tuning and training-from-scratch regimes. Crucially, these gains are achieved without compromising accuracy; in fact, performance is consistently preserved and often enhanced across a diverse set of downstream tasks.

Despite the growing interest in jailbreaks as an effective red-teaming tool for building safe and responsible large language models (LLMs), flawed evaluation system designs have led to significant discrepancies in their effectiveness assessments. With a systematic measurement study based on 37 jailbreak studies since 2022, we find that existing evaluation systems lack case-specific criteria, resulting in misleading conclusions about their effectiveness and safety implications. In this paper, we introduce GuidedBench, a novel benchmark comprising a curated harmful question dataset and GuidedEval, an evaluation system integrated with detailed case-by-case evaluation guidelines. Experiments demonstrate that GuidedBench offers more accurate evaluations of jailbreak performance, enabling meaningful comparisons across methods. GuidedEval reduces inter-evaluator variance by at least 76.03%, ensuring reliable and reproducible evaluations. We reveal why existing jailbreak benchmarks fail to evaluate accurately and suggest better evaluation practices.

While LLMs have demonstrated medical knowledge and conversational ability, their deployment in clinical practice raises new risks: patients may place greater trust in LLM-generated responses than in nurses' professional judgments, potentially intensifying nurse–patient conflicts. Such risks highlight the urgent need of evaluating whether LLMs align with the core nursing values upheld by human nurses. This work introduces the first benchmark for nursing value alignment, consisting of five core value dimensions distilled from international nursing codes: _Altruism_, _Human Dignity_, _Integrity_, _Justice_, and _Professionalism_. We define two-level tasks on the benchmark, considering the two characteristics of emerging nurse–patient conflicts. The **Easy-Level** dataset consists of 2,200 value-aligned and value-violating instances, which are collected through a five-month longitudinal field study across three hospitals of varying tiers; The **Hard-Level** dataset is comprised of 2,200 dialogue-based instances that embed contextual cues and subtle misleading signals, which increase adversarial complexity and better reflect the subjectivity and bias of narrators in the context of emerging nurse-patient conflicts. We evaluate a total of 23 SoTA LLMs on their ability to align with nursing values, and find that general LLMs outperform medical ones, and _Justice_ is the hardest value dimension. As the first real-world benchmark for healthcare value alignment, NurValues provides novel insights into how LLMs navigate ethical challenges in clinician–patient interactions.

Using intelligent systems to perceive psychological and social behaviors, that is, the underlying affective, cognitive, and pathological states that are manifested through observable behaviors and social interactions, remains a challenge due to their complex, multifaceted, and personalized nature. Existing work tackling these dimensions through specialized datasets and single-task systems often miss opportunities for scalability, cross-task transfer, and broader generalization. To address this gap, we curate Human Behavior Atlas, a unified benchmark of diverse behavioral tasks designed to support the development of foundation models for understanding psychological and social behaviors. Human Behavior Atlas comprises over 100,000 samples spanning text, audio, and visual modalities, covering tasks on *affective states*, *cognitive states*, *pathologies*, and *social processes*. Our unification efforts can reduce redundancy and cost, enable training to scale efficiently across tasks, and enhance generalization of behavioral features across domains. On Human Behavior Atlas, we train three models: Omnisapiens-7B SFT, Omnisapiens-7B BAM, and Omnisapiens-7B RL. We show that training on Human Behavior Atlas enables models to consistently outperform existing multimodal LLMs across diverse behavioral tasks. Pretraining on Human Behavior Atlas also improves transfer to novel behavioral datasets; with the targeted use of behavioral descriptors yielding meaningful performance gains. The benchmark, models, and codes can be found at: https://github.com/MIT-MI/human_behavior_atlas.

Transferability estimation metrics are used to find a high-performing pre-trained model for a given target task without fine-tuning models and without access to the source dataset. Despite the growing interest in developing such metrics, the benchmarks used to measure their progress have gone largely unexamined. In this work, we empirically show the shortcomings of widely used benchmark setups to evaluate transferability estimation metrics. We argue that the benchmarks on which these metrics are evaluated are fundamentally flawed. We empirically demonstrate that their unrealistic model spaces and static performance hierarchies artificially inflate the perceived performance of existing metrics, to the point where simple, dataset-agnostic heuristics can outperform sophisticated methods. Our analysis reveals a critical disconnect between current evaluation protocols and the complexities of real-world model selection. To address this, we provide concrete recommendations for constructing more robust and realistic benchmarks to guide future research in a more meaningful direction.

Recent advancements in algorithms for local intrinsic dimension (LID) estimation have been closely tied to progress in neural networks (NN). However, NN architectures are often tailored to specific domains, such as audio or image data, incorporating inductive biases that limit their transferability across domains. Moreover, existing LID estimation methods leveraging these architectures are typically evaluated on either overly simplistic benchmarks or domain datasets where the true LID is unknown, resulting in potentially erroneous evaluations. To close this research gap, we first isolate problematic aspects of LID estimation and leverage them to analyze the limitations of state-of-the-art methods. Our approach employs several techniques to create LID benchmarks for arbitrary domains, including the introduction of a method to transform any manifold into the domain while preserving the manifold structure, thereby addressing challenges posed by biases in neural network-based methods. Our comparative analysis reveals critical limitations and identifies new directions for future development in LID estimation methods. Code will be available on github when published.

Detecting missing persons in forest environments remains a challenge, as dense canopy cover often conceals individuals from detection in top-down or oblique aerial imagery typically captured by Unmanned Aerial Vehicles (UAVs). While UAVs are effective for covering large, inaccessible areas, their aerial perspectives often miss critical visual cues beneath the forest canopy. This limitation underscores the need for under-canopy perspectives better suited for detecting missing persons in such environments. To address this gap, we introduce ForestPersons, a novel large-scale dataset specifically designed for under-canopy person detection. ForestPersons contains 96,482 images and 204,078 annotations collected under diverse environmental and temporal conditions. Each annotation includes a bounding box, pose, and visibility label for occlusion-aware analysis. ForestPersons provides ground-level and low-altitude perspectives that closely reflect the visual conditions encountered by Micro Aerial Vehicles (MAVs) during forest Search and Rescue (SAR) missions. Our baseline evaluations reveal that standard object detection models, trained on prior large-scale object detection datasets or SAR-oriented datasets, show limited performance on ForestPersons. This indicates that prior benchmarks are not well aligned with the challenges of missing person detection under the forest canopy. We offer this benchmark to support advanced person detection capabilities in real-world SAR scenarios. The dataset is publicly available at https://huggingface.co/datasets/anonreviewer2026/under-canopy-benchmark-anon.

AI is transforming scientific research by revealing new ways to understand complex physical systems, but its impact remains constrained by the lack of large, high-quality domain-specific datasets. A rich, largely untapped resource lies in non-Hermitian quantum physics, where the energy spectra of crystals form intricate geometries on the complex plane—termed as $\textit{Hamiltonian spectral graphs}$. Despite their significance as fingerprints for electronic behavior, their systematic study has been intractable due to the reliance on manual extraction. To unlock this potential, we introduce $\textbf{Poly2Graph}$ (https://github.com/sarinstein-yan/Poly2Graph): a high-performance, open-source pipeline that automates the mapping of 1-D crystal Hamiltonians to spectral graphs. Using this tool, we present $\textbf{HSG-12M}$ (https://github.com/sarinstein-yan/HSG-12M): a dataset containing 11.6 million static and 5.1 million dynamic Hamiltonian spectral graphs across 1401 characteristic-polynomial classes, distilled from 177 TB of spectral potential data. Crucially, HSG-12M is the first large-scale dataset of $\textit{spatial multigraphs}$—graphs embedded in a metric space where multiple geometrically distinct trajectories between two nodes are retained as separate edges. This simultaneously addresses a critical gap, as existing graph benchmarks overwhelmingly assume simple, non-spatial edges, discarding vital geometric information. Benchmarks with popular GNNs expose new challenges in learning spatial multi-edges at scale. Beyond its practical utility, we show that spectral graphs serve as universal topological fingerprints of polynomials, vectors, and matrices, forging a new algebra-to-graph link. HSG-12M lays the groundwork for data-driven scientific discovery in condensed matter physics, new opportunities in geometry-aware graph learning and beyond.

We introduce WorldSense, the first benchmark to assess the multi-modal video understanding, that simultaneously encompasses visual, audio, and text inputs. In contrast to existing benchmarks, our WorldSense has several features: (i) collaboration of omni-modality, we design the evaluation tasks to feature a strong coupling of audio and video, requiring models to effectively utilize the synergistic perception of omni-modality; (ii) diversity of videos and tasks, WorldSense encompasses a diverse collection of 1,662 audio-visual synchronised videos, systematically categorized into 8 primary domains and 67 fine-grained subcategories to cover the broad scenarios, and 3,172 multi-choice QA pairs across 26 distinct tasks to enable the comprehensive evaluation; (iii) high-quality annotations, all the QA pairs are manually labeled by 80 expert annotators with multiple rounds of correction to ensure quality. Based on our WorldSense, we extensively evaluate various state-of-the-art models. The experimental results indicate that existing models face significant challenges in understanding real-world scenarios (65.1% best accuracy). By analyzing the limitations of current models, we aim to provide valuable insight to guide development of real-world understanding. We hope our WorldSense can provide a platform for evaluating the ability in constructing and understanding coherent contexts from omni-modality.