ICLR 2026 论文列表

Molecular representations (MRs) that capture 3D conformations are critical for applications such as reaction prediction, drug design, and material discovery. Yet despite the rapid development of molecular representation models, there is no comprehensive benchmark to evaluate their treatment of 3D conformational information. We introduce 3DCS, the first benchmark for 3D Conformational Sensitivity in MRs. 3DCS evaluates whether representations within the same molecule (i) preserve geometric variation, (ii) capture chirality, and (iii) reflect the energy landscape. To enable this, we curate three large-scale datasets ($>$1M molecules, $\sim$10M conformers) spanning relaxed torsional scans, chiral drug candidates, and AIMD trajectories, and propose a unified Geometry–Chirality–Energy (GCE) evaluation framework. Empirical analysis reveals that while modern data-driven MRs are highly geometry-sensitive, they inconsistently handle chirality and poorly align with energy, which is often overlooked. 3DCS thus provides the first rigorous benchmark for developing physically grounded, functionally reliable 3D molecular representations.

The rapid advancement of multimodal large language models (MLLMs) has greatly prompted the video interpretation task, and numerous works have been proposed to explore and benchmark the cognition and basic visual reasoning capabilities of MLLMs. However, practical applications on social media platforms demand MLLMs that can emulate user-like thinking and behavior when interpreting user-generated videos, which has been rarely studied in current research. To bridge the gap and get closer to general practical artificial intelligence (AI), we first construct **MIMIC-Data**, a large-scale dataset containing 150K+ user-shared videos with corresponding information including captions, tags, comments, *etc.* Then, we present **MIMIC-Bench**, a large-scale benchmark building upon curated 4,000 user-shared videos from MIMIC-Data, which is designed to evaluate user-like thinking and mimicking capabilities of MLLMs in real-world video contexts. MIMIC-Bench not only supports user-like thinking challenges including creator intent, user feedback interpretation, *etc.*, but also introduces a novel comment imitation task to assess whether MLLMs can generate human-like responses to video content. Based on MIMIC-Data and MIMIC-Bench, we develop **MIMIC-Chat**, which integrates spatial and temporal features into a large language model, and finetunes the model to perform user-like thinking and mimicking tasks. Extensive experiments conducted based on 24 existing MLLMs and our MIMIC-Chat model show that current MLLMs exhibit limited capabilities to perform human-like thinking and responses, and MIMIC-Chat performs better to some extent. We hope MIMIC-Bench can contribute to the advancement of human-aligned video understanding in the multi-modal era. The MIMIC-Data, MIMIC-Bench, and MIMIC-Chat will be released upon the publication.

Zero-shot text classification (ZSC) offers the promise of eliminating costly task-specific annotation by matching texts directly to human-readable label descriptions. While early approaches have predominantly relied on cross-encoder models fine-tuned for natural language inference (NLI), recent advances in text-embedding models, rerankers, and instruction-tuned large language models (LLMs) have challenged the dominance of NLI-based architectures. Yet, systematically comparing these diverse approaches remains difficult. Existing evaluations, such as MTEB, often incorporate labeled examples through supervised probes or fine-tuning, leaving genuine zero-shot capabilities underexplored. To address this, we introduce __BTZSC__, a comprehensive benchmark of $22$ public datasets spanning sentiment, topic, intent, and emotion classification, capturing diverse domains, class cardinalities, and document lengths. Leveraging BTZSC, we conduct a systematic comparison across four major model families, NLI cross-encoders, embedding models, rerankers and instruction-tuned LLMs, encompassing $38$ public and custom checkpoints. Our results show that: (i) modern rerankers, exemplified by _Qwen3-Reranker-8B_, set a new state-of-the-art with macro $F_1 = 0.72$; (ii) strong embedding models such as _GTE-large-en-v1.5_ substantially close the accuracy gap while offering the best trade-off between accuracy and latency; (iii) instruction-tuned LLMs at 4-12B parameters achieve competitive performance (macro $F_1$ up to $0.67$), excelling particularly on topic classification but trailing specialized rerankers; (iv) NLI cross-encoders plateau even as backbone size increases; and (v) scaling primarily benefits rerankers and LLMs over embedding models. BTZSC and accompanying evaluation code are publicly released to support fair and reproducible progress in zero-shot text understanding.

As Text-to-Image (TTI) diffusion models become increasingly influential in content creation, growing attention is being directed toward their societal and cultural implications. While prior research has primarily examined demographic and cultural biases, the ability of these models to accurately represent historical contexts remains largely underexplored. To address this gap, we introduce a benchmark for evaluating how TTI models depict historical contexts. The benchmark combines HistVis, a dataset of 30,000 synthetic images generated by three state-of-the-art diffusion models from carefully designed prompts covering universal human activities across multiple historical periods, with a reproducible evaluation protocol. We evaluate generated imagery across three key aspects: (1) Implicit Stylistic Associations: examining default visual styles associated with specific eras; (2) Historical Consistency: identifying anachronisms such as modern artifacts in pre-modern contexts; and (3) Demographic Representation: comparing generated racial and gender distributions against historically plausible baselines. Our findings reveal systematic inaccuracies in historically themed generated imagery, as TTI models frequently stereotype past eras by incorporating unstated stylistic cues, introduce anachronisms, and fail to reflect plausible demographic patterns. By providing a reproducible benchmark for historical representation in generated imagery, this work provides an initial step toward building more historically accurate TTI models.

The Minimum Description Length (MDL) principle offers a formal framework for applying Occam's razor in machine learning. However, its application to neural networks such as Transformers is challenging due to the lack of a principled, universal measure for model complexity. This paper introduces the theoretical notion of asymptotically optimal description length objectives, grounded in the theory of Kolmogorov complexity. We establish that a minimizer of such an objective achieves optimal compression, for any dataset, up to an additive constant, in the limit as model resource bounds increase. We prove that asymptotically optimal objectives exist for Transformers, building on a new demonstration of their computational universality. We further show that such objectives can be tractable and differentiable by constructing and analyzing a variational objective based on an adaptive Gaussian mixture prior. Our empirical analysis shows that this variational objective selects for a low-complexity solution with strong generalization on an algorithmic task, but standard optimizers fail to find such solutions from a random initialization, highlighting key optimization challenges. More broadly, by providing a theoretical framework for identifying description length objectives with strong asymptotic guarantees, we outline a potential path towards training neural networks that achieve greater compression and generalization.

One of the fundamental problems in digital agents is their lack of understanding of their environment. For instance, a web browsing agent may get lost in unfamiliar websites, uncertain what pages must be visited to achieve its goals. To address this, we propose Go-Browse, a method for automatically collecting diverse and realistic web agent data at scale through structured exploration of web environments. Go-Browse achieves efficient exploration by framing data collection as a graph search, enabling reuse of information across exploration episodes. We instantiate our method on the WebArena benchmark, collecting a dataset of 10K successful task-solving trajectories and 40K interaction steps across 100 URLs. Fine-tuning a 7B parameter language model on this dataset achieves a success rate of 21.7% on the WebArena benchmark, beating GPT-4o mini by 2.4% and exceeding current state-of-the-art results for sub-10B parameter models by 2.9%.

Diffusion models suffer from substantial computational overhead due to their inherently iterative inference process. While feature caching offers a promising acceleration strategy by reusing intermediate outputs across timesteps, naive reuse often incurs noticeable quality degradation. In this work, we formally analyze the cumulative error introduced by caching and decompose it into two principal components: feature shift error, caused by inaccuracies in cached outputs, and step amplification error, which arises from error propagation under fixed timestep schedules. To address these issues, we propose ERTACache a principled caching framework that jointly rectifies both error types. Our method employs an offline residual profiling stage to identify reusable steps, dynamically adjusts integration intervals via a trajectory-aware correction coefficient, and analytically approximates cache-induced errors through a closed-form residual linearization model. Together, these components enable accurate and efficient sampling under aggressive cache reuse. Extensive experiments across standard image and video generation benchmarks show that ERTACache achieves up to 2x inference speedup while consistently preserving or even improving visual quality. Notably, on the state-of-the-art Wan 2.1 video diffusion model, ERTACache delivers 2x acceleration with minimal VBench degradation, effectively maintaining baseline fidelity while significantly improving efficiency.

Fully open multimodal large language models (MLLMs) currently lag behind proprietary counterparts, primarily due to a significant gap in data quality for supervised fine-tuning (SFT). Existing open-source datasets are often plagued by widespread noise and a critical deficit in complex reasoning data, such as Chain-of-Thought (CoT), which hinders the development of advanced model capabilities. Addressing these challenges, our work makes three primary contributions. First, we introduce Honey-Data-15M, a new SFT dataset comprising approximately 15 million QA pairs, processed through multiple cleaning techniques and enhanced with a novel dual-level (short and long) CoT enrichment strategy. Second, we introduce HoneyPipe, the data curation pipeline, and its underlying framework DataStudio, providing the community with a transparent and adaptable methodology for data curation that moves beyond static dataset releases. Finally, to validate our dataset and pipeline, we train Bee-8B, an 8B model on Honey-Data-15M. Experiments show that Bee-8B establishes a new state-of-the-art (SOTA) for fully open MLLMs, achieving performance that is competitive with, and in some cases surpasses, recent semi-open models such as InternVL3.5-8B. A comprehensive ablation study further dissects the impact of our data curation process, revealing that each stage provides significant performance gains across a wide range of benchmarks. Our work delivers to the community a suite of foundational resources, including: the Honey-Data-15M corpus; the full-stack suite comprising HoneyPipe and DataStudio; training recipes; an evaluation harness; and the model weights. This effort demonstrates that a principled focus on data quality is a key pathway to developing fully open MLLMs that are highly competitive with their semi-open counterparts.

Machine unlearning aims to remove specific content from trained models while preserving overall performance. However, the phenomenon of benign relearning, in which forgotten information reemerges even from benign fine-tuning data, reveals that existing unlearning methods remain fundamentally fragile. A common explanation attributes this effect to topical relevance, but we find this account insufficient. Through systematic analysis, we demonstrate that syntactic similarity, rather than topicality, is the primary driver: across benchmarks, syntactically similar data consistently trigger recovery even without topical overlap, due to their alignment in representations and gradients with the forgotten content. Motivated by this insight, we introduce syntactic diversification, which paraphrases the original forget queries into heterogeneous structures prior to unlearning. This approach effectively suppresses benign relearning, accelerates forgetting, and substantially alleviates the trade-off between unlearning efficacy and model utility.

Large language models (LLMs) show the promise in supporting scientific research implementation, yet their ability to generate correct and executable code remains limited. Existing works largely adopt one-shot settings, ignoring the iterative and feedback-driven nature of realistic workflows of scientific research development. To address this gap, we present RECODE, a benchmark of 102 tasks from research papers and repositories that evaluates LLMs through multi-turn interactions with human feedback. It includes structured instructions, unit tests, and a five-level feedback hierarchy to reflect realistic researcher–agent collaboration. We further present ReCodeAgent, a framework that integrates feedback into iterative code generation. Experimentswith leading LLMs, including GPT-5, Claude-Sonnet-4, DeepSeek-V3.1, and Gemini 2.5, show substantial performance gains with richer feedback, while also highlighting ongoing challenges in the generation of complex research code. RECODE establishes a foundation for developing adaptive, feedback-driven LLM agents in scientific research implementation.

We construct VisualPRM400K, a dataset comprising about 400K multimodal process supervision data. Building upon this dataset, we develop VisualPRM, an advanced multimodal Process Reward Model (PRM) capable of estimating the value score of each step during the reasoning process. Under the Best-of-N evaluation setting, our model improves the reasoning performance of three types of MLLMs and four different model scales. Even when applied to the highly capable InternVL2.5-78B, it achieves a 5.9-point improvement across seven multimodal reasoning benchmarks. Experimental results show that the PRM model trained on our VisualPRM400K exhibits superior performance compared to Outcome Reward Models and Self-Consistency during BoN evaluation. To further facilitate the development of multimodal PRMs, we construct VisualProcessBench, a benchmark designed to measure the abilities of PRMs and MLLMs to detect incorrect steps in multimodal reasoning tasks. We hope that our work can inspire more future research and contribute to the development of MLLMs. Our model, data, and benchmark will be released.

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, tabular data, CIFAR-10) 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.

Model-based methods for offline Reinforcement Learning transfer extensive policy exploration and evaluation to data-driven dynamics models, effectively saving real-world samples in the offline setting. We expect the dynamics model to allow the policy to roll out full-horizon episodes, which is crucial for ensuring sufficient exploration and reliable evaluation. However, many previous dynamics models exhibit limited capability in long-horizon prediction. This work follows the paradigm of the Any-step Dynamics Model (ADM) that improves future predictions by reducing bootstrapping prediction to direct prediction. We structurally decouple each recurrent forward of the RNN cell from the backtracked state and propose the second version of ADM (ADM-v2), making the direct prediction more flexible. ADM-v2 not only enhances the accuracy of direct predictions for making full-horizon roll-outs but also supports parallel estimation of the any-step prediction uncertainty to improve efficiency. The results on DOPE validate the reliability of ADM-v2 for policy evaluation. Moreover, via full-horizon roll-out, ADM-v2 for policy optimization enables substantial advancements, whereas other dynamics models degrade due to long-horizon error accumulation. We are the first to achieve SOTA under the full-horizon roll-out setting on both D4RL and NeoRL.

The aspiration for artificial general intelligence, fueled by the rapid progress of multimodal understanding, demands models to understand humans in diverse and complex scenarios, as humans manifests intelligence and embody the world. We propose HumanPCR, an evaluation suite for probing MLLMs’ capacity in human-centric visual contexts across three hierarchical levels: Perception, Comprehension, and Reasoning (denoted by Human-P, Human-C, and Human-R, respectively). Human-P and Human-C consist of over 6,000 multiple-choice questions evaluating 34 fine-grained tasks covering 9 essential dimensions. Human-R presents a manually curated challenging video reasoning test that requires integrating multiple visual evidence, proactively extracting implicit context beyond question cues, and applying human-like expertise. Each question includes human-annotated Chain-of-Thought (CoT) rationales with key visual evidence to support further research. Extensive evaluations on over 30 state-of-the-art models exhibit significant challenges in human-centric visual understanding, particularly in tasks involving detailed space perception, temporal understanding, and mind modeling. The analysis of Human-R further exposes a critical failure in reasoning: models struggle to proactively gather necessary visual evidence, instead showing a faulty reliance on query-prompted cues, with advanced techniques offering only marginal gains. We hope HumanPCR and our findings will advance the development, evaluation, and human-centric applications of multimodal models.

AI models have made significant strides in recent years in their ability to describe and answer questions about real-world images. They have also made progress in the ability to converse with users in real-time using audio input. This raises the question: have we reached the point where AI models, connected to a camera and microphone, can converse with users in real-time about scenes and events that are unfolding live in front of the camera? This has been a long-standing goal in AI and is a prerequisite for real-world AI assistants and humanoid robots to interact with humans in everyday situations. In this work, we introduce a new dataset and benchmark, the Interactive Video Dataset (IVD), which allows us to assess the extent to which existing models can support these abilities, and to what degree these capabilities can be instilled through fine-tuning. The dataset is based on a simple question-answering setup, where users ask questions that the system has to answer, in real-time, based on the camera and audio input. We show that existing models fall far behind human performance on this task, and we identify the main sources for the performance gap. However, we also show that for many of the required perceptual skills, fine-tuning on this form of data can significantly reduce this gap.

Peer review is a critical process for ensuring the integrity of published scientific research. Confidence in this process is predicated on the assumption that experts in the relevant domain give careful consideration to the merits of manuscripts which are submitted for publication. With the recent rapid advancements in large language models (LLMs), a new risk to the peer review process is that negligent reviewers will rely on LLMs to perform the often time consuming process of reviewing a paper. However, there is a lack of existing resources for benchmarking the detectability of AI text in the domain of peer review. To address this deficiency, we introduce a comprehensive dataset containing a total of 788,984 AI-written peer reviews paired with corresponding human reviews, covering 8 years of papers submitted to each of two leading AI research conferences (ICLR and NeurIPS). We use this new resource to evaluate the ability of 18 existing AI text detection algorithms to distinguish between peer reviews fully written by humans and different state-of-the-art LLMs. Additionally, we explore a context-aware detection method called Anchor, which leverages manuscript content to detect AI-generated reviews, and analyze the sensitivity of detection models to LLM-assisted editing of human-written text. Our work reveals the difficulty of identifying AI-generated text at the individual peer review level, highlighting the urgent need for new tools and methods to detect this unethical use of generative AI. To support future research and reproducibility, we will publicly release our dataset upon publication.

Dataset distillation aims to synthesize compact yet informative datasets from large ones. A significant challenge in this field is achieving a trifecta of diversity, generalization, and representativeness in a single distilled dataset. Although recent generative dataset distillation methods adopt powerful diffusion models as their foundation models, the inherent representativeness prior in diffusion models is overlooked. Consequently, these approaches often necessitate the integration of external constraints to enhance data quality. To address this, we propose Diffusion As Priors (DAP), which formalizes representativeness by quantifying the similarity between synthetic and real data in feature space using a Mercer kernel. We then introduce this prior as guidance to steer the reverse diffusion process, enhancing the representativeness of distilled samples without any retraining. Extensive experiments on large-scale datasets, such as ImageNet-1K and its subsets, demonstrate that DAP outperforms state-of-the-art methods in generating high-fidelity datasets while achieving superior cross-architecture generalization. Our work not only establishes a theoretical connection between diffusion priors and the objectives of dataset distillation but also provides a practical, training-free framework for improving the quality of the distilled dataset.

Recent progress in large language models (LLMs) has outpaced the development of effective evaluation methods. Evaluating LLMs with static, task-specific benchmarks is increasingly fragile due to contamination and saturation, and it fails to capture interactive reasoning. We introduce Teach2Eval, which reframes evaluation as teaching: a candidate model guides weaker students, and the students’ gains constitute the score. This interaction yields robustness to contamination and exposes orthogonal abilities with fine-grained metrics across Application, Judgment, Guidance, and Reflection. The framework scales automatically by exploiting natural error distributions from weak students, requiring neither bespoke rubrics nor human graders. Across 30 LLMs and 60 datasets, Teach2Eval achieves Spearman above 0.95 with human-preference leaderboards (e.g., Chatbot Arena/LiveBench), surpassing direct baselines, while offering actionable training signals (capability hierarchies, early overfitting) at low cost.

Multimodal Large Language Models (MLLMs) combine the linguistic strengths of LLMs with the ability to process multimodal data, enabling them to address a broader range of tasks. This progression highlights a shift from language-only reasoning to integrated vision–language reasoning in children's development. Inspired by the Wechsler Intelligence Scales, we introduce KidGym, a comprehensive 2D grid-based benchmark for assessing five essential capabilities of MLLMs: execution, perception reasoning, learning, memory, and planning. The benchmark comprises 12 unique tasks, each targeting at least one core capability, specifically designed to gauge MLLMs' adaptability and developmental potential, mirroring the stages of children's cognitive growth. Additionally, our tasks encompass diverse scenarios and objects with randomly generated layouts, ensuring more accurate and robust evaluation of MLLM capabilities. KidGym is designed to be fully user-customizable and extensible, allowing researchers to create new evaluation scenarios and adjust difficulty levels to accommodate the rapidly growing MLLM community. Through evaluation of state-of-the-art MLLMs using KidGym, we identified significant insights into model capabilities and revealed important limitations of current status. We release our benchmark at: https://kidgym.github.io/KidGym-Website/.