ICLR 2026 论文列表

Understanding long videos requires Multimodal Large Language Models (MLLMs) to grasp multi-timescale information, often organized in hierarchies. However, current long-video understanding benchmarks either overlook multi-timescale design or distribute questions targeting different timescales across different videos. This approach entangles timescales with video content, thereby hindering a clear assessment of MLLM multi-timescale performance. To address this, we introduce ScaleLong, the first benchmark to disentangle these factors by embedding questions targeting four hierarchical timescales\textemdash clip (seconds), shot (tens of seconds), event (minutes), and story (hours)\textemdash all within the same video content. This ``within-content'' multi-timescale questioning design enables direct comparison of model performance across timescales on identical videos. ScaleLong features 269 videos (avg. 86 min) from 5 main categories and 36 sub-categories, with 4–8 carefully designed questions, with at least one question targeting each timescale. Evaluating 22 MLLMs reveals a distinct U-shaped performance trend: higher accuracy at the shortest (clip) and longest (story) timescales, with a dip at intermediate levels. Furthermore, ablation studies demonstrate that increased visual token capacity consistently enhances reasoning across all timescales. ScaleLong offers a crucial fine-grained, multi-timescale benchmark for advancing MLLM capabilities in long-video understanding. The code and dataset are available at \url{https://anonymous.4open.science/r/ScaleLong-7717}.

Proper initialisation strategy is of primary importance to mitigate gradient explosion or vanishing when training neural networks. Yet, the impact of initialisation parameters still lacks a precise theoretical understanding for several well-established architectures. Here, we propose a new initialisation for networks with sinusoidal activation functions such as \texttt{SIREN}, focusing on gradients control, their scaling with network depth, their impact on training and on generalization. To achieve this, we identify a closed-form expression for the initialisation of the parameters, differing from the original \texttt{SIREN} scheme. This expression is derived from fixed points obtained through the convergence of pre-activation distribution and the variance of Jacobian sequences. Controlling both gradients and targeting vanishing pre-activation helps preventing the emergence of inappropriate frequencies during estimation, thereby improving generalization. We further show that this initialisation strongly influences training dynamics through the Neural Tangent Kernel framework (NTK). Finally, we benchmark \texttt{SIREN} with the proposed initialisation against the original scheme and other baselines on function fitting and image reconstruction. The new initialisation consistently outperforms state-of-the-art methods across a wide range of reconstruction tasks, including those involving physics-informed neural networks.

DNA methylation (DNAm) is a key epigenetic modification that regulates gene expression and is pivotal in development and disease. However, profiling DNAm at genome scale is challenging: of $\textasciitilde$28 million CpG sites in the human genome, only about 1–3\% are typically assayed in common datasets due to technological limitations and cost. Recent deep learning approaches, including masking-based generative Transformer models, have shown promise in capturing DNAm–gene expression relationships, but they rely on partially observed DNAm values for unmeasured CpGs and cannot be applied to completely unmeasured samples. To overcome this barrier, we introduce MethylProphet, a gene-guided, context-aware Transformer model for whole-genome DNAm inference without any measured DNAm input. MethylProphet compresses comprehensive gene expression profiles ($\textasciitilde$25K genes) through an efficient bottleneck multilayer perceptron, and encodes local CpG sequence context with a specialized DNA tokenizer. These representations are integrated by a Transformer encoder to predict site-specific methylation levels. Trained on large-scale pan-tissue whole-genome bisulfite sequencing data from ENCODE (1.6 billion CpG–sample pairs, $\textasciitilde$322 billion tokens), MethylProphet demonstrates strong performance in hold-out evaluations, accurately inferring DNAm at unmeasured CpGs and generalizing to unseen samples. Furthermore, application to TCGA pan-cancer data (chromosome 1, 9,194 samples; $\textasciitilde$450 million training pairs, 91 billion tokens) highlights its potential for pan-cancer whole-genome methylome imputation. MethylProphet offers a powerful and scalable foundation model for epigenetics, providing high-resolution methylation landscape reconstruction and advancing both biological research and precision medicine.

Log-likelihood evaluation enables important capabilities in generative models, including model comparison, certain fine-tuning objectives, and many downstream applications. Yet paradoxically, some of today's best generative models -- diffusion and flow-based models -- still require hundreds to thousands of neural function evaluations (NFEs) to compute a single likelihood. While recent distillation methods have successfully accelerated sampling to just a few steps, they achieve this at the cost of likelihood tractability: existing approaches either abandon likelihood computation entirely or still require expensive integration over full trajectories. We present fast flow joint distillation (F2D2), a framework that simultaneously reduces the number of NFEs required for both sampling and likelihood evaluation by two orders of magnitude. Our key insight is that in continuous normalizing flows, the coupled ODEs for sampling and likelihood are computed from a shared underlying velocity field, allowing us to jointly distill both the sampling trajectory and cumulative divergence using a single model. F2D2 is modular, compatible with existing flow-based few-step sampling models, and requires only an additional divergence prediction head. Experiments demonstrate F2D2's capability of achieving accurate log-likelihood with few-step evaluations while maintaining high sample quality, solving a long-standing computational bottleneck in flow-based generative models.

Recently, large time series models (LTSM) have become popular and important because they exhibit characteristics similar to large language models, such as flexible context length, scalability, and task generality, outperforming the advanced task-specific models in the domain. However, existing research indicates that the pre-trained LTSM can show a poor non-convex loss landscape (indicating poor trainability). Hence, directly fine-tuning pre-trained LTSM shows overfitting, which leads to poor fine-tuning performance, even worse than training from scratch on the downstream datasets. This severely diminishes the value of the pre-trained LTSM. To address this, we propose a new fine-tuning method called Smoothed Full Fine-tuning (SFF). Specifically, before fine-tuning, we first construct an auxiliary LTSM with a smooth loss landscape (indicating good trainability) through random initialization. Second, we utilize it to smooth the loss landscape of the pre-trained LTSM through linear interpolation between their weights. As a result, the smoothed LTSM acquires good trainability while retaining good pre-training knowledge, thereby achieving better performance when fine-tuned on the downstream dataset. We also explain why SFF is effective from the perspective of optimization theory: interpolation perturbs sharp minima without obviously harming originally flat regions, thereby aiding sharp minima escape to better and smoother basins. Extensive experiments on popular datasets show that our method indeed improves the performance of eight popular LTSMs, e.g., Timer, TimesFM, MOMENT, UniTS, MOIRAI, Chronos, TTMs, and Sundial, in different downstream tasks.

Spatial embodied intelligence often operates under partial observability, where agents must act to acquire missing information rather than passively consume complete observations. In such settings, progress depends on actively selecting informative actions that reduce uncertainty and support the construction of spatial understanding. While multimodal foundation models have shown strong performance on passive multimodal perception and reasoning tasks, their ability to support active, self-directed exploration under partial observability has not been systematically studied. In particular, it remains unclear whether and how these models can decide what to observe next in order to build and maintain a coherent spatial belief over time. We therefore propose \tos, defined as an agent’s ability to actively acquire information through self-directed, active exploration and to construct, revise, and exploit a spatial belief from sequential, partial observations. We implement \tos using a benchmark with textual and visual environments. Rather than solving specific tasks, the goal is curiosity-driven exploration to build a complete, accurate spatial belief. A core innovation is spatial belief probing: we prompt it to reveal its internal spatial belief as a cognitive map at each step, letting us measure the quality of its underlying spatial model. Our evaluation of state-of-the-art models on a suite of downstream tasks reveals critical bottlenecks: (1) \textbf{The Active-Passive Gap}: Performance degrades when agents must autonomously gather information (e.g., \textsc{GPT-5.2}: $0.57{\to}0.46$); (2) \textbf{Inefficiency}: Models explore in an unsystematic way and with high redundancy, failing to match the efficiency of program-based proxies while producing no better results. Through belief probing, we diagnose that perception acts as an initial bottleneck, yet global beliefs suffer further from \textbf{instability} that causes spatial knowledge to degrade over time. Finally, using a false belief paradigm to test belief revision, we uncover \textbf{Belief Inertia} where agents fail to overwrite obsolete priors. This issue exists in text agents but is notably severe in vision-based models.

Large Reasoning Models (LRMs) have demonstrated impressive performance on complex tasks, including logical puzzle games that require deriving solutions satisfying all constraints. However, whether they can flexibly apply appropriate rules to varying conditions, particularly when faced with non-canonical game variants, remains an open question. Existing corpora focus on popular puzzles like 9x9 Sudoku, risking overfitting to canonical formats and memorization of solution patterns, which can mask deficiencies in understanding novel rules or adapting strategies to new variants. To address this, we introduce **HardcoreLogic**, a challenging benchmark of over 5,000 puzzles across 10 games, designed to test the robustness of LRMs on the "long-tail" of logical games. HardcoreLogic systematically transforms canonical puzzles through three dimensions: **Increased Complexity (IC)**, **Uncommon Elements (UE)**, and **Unsolvable Puzzles (UP)**, reducing reliance on shortcut memorization. Evaluations on a diverse set of LRMs reveal significant performance drops, even for models achieving top scores on existing benchmarks, indicating heavy reliance on memorized stereotypes. While increased complexity is the dominant source of difficulty, models also struggle with subtle rule variations that do not necessarily increase puzzle difficulty. Our systematic error analysis on solvable and unsolvable puzzles further highlights gaps in genuine reasoning. Overall, HardcoreLogic exposes the limitations of current LRMs and establishes a benchmark for advancing high-level logical reasoning.

Medical question answering (QA) benchmarks often focus on multiple-choice or fact-based tasks, leaving open-ended answers to real patient questions underexplored. This gap is particularly critical in mental health, where patient questions often mix symptoms, treatment concerns, and emotional needs, requiring answers that balance clinical caution with contextual sensitivity. We present CounselBench, a large-scale benchmark developed with 100 mental health professionals to evaluate and stress-test large language models (LLMs) in realistic help-seeking scenarios. The first component, CounselBench-EVAL, contains 2,000 expert evaluations of answers from GPT-4, LLaMA 3, Gemini, and online human therapists on patient questions from the public forum CounselChat. Each answer is rated across six clinically grounded dimensions, with span-level annotations and written rationales. Expert evaluations show that while LLMs achieve high scores on several dimensions, they also exhibit recurring issues, including unconstructive feedback, overgeneralization, and limited personalization or relevance. Responses were frequently flagged for safety risks, most notably unauthorized medical advice. Follow-up experiments show that LLM judges systematically overrate model responses and overlook safety concerns identified by human experts. To probe failure modes more directly, we construct CounselBench-Adv, an adversarial dataset of 120 expert-authored mental health questions designed to trigger specific model issues. Expert evaluation of 1,080 responses from nine LLMs reveals consistent, model-specific failure patterns. Together, CounselBench establishes a clinically grounded framework for benchmarking LLMs in mental health QA.

Online services rely on CAPTCHAs as a first line of defense against automated abuse, yet recent advances in multi-modal large language models (MLLMs) have eroded the effectiveness of conventional designs that focus on text recognition or 2D image understanding. To address this challenge, we present **Spatial CAPTCHA**, a novel human-verification framework that leverages fundamental differences in spatial reasoning between humans and MLLMs. Unlike existing CAPTCHAs that rely on low-level perception tasks vulnerable to modern AI, Spatial CAPTCHA generates dynamic questions requiring geometric reasoning, perspective-taking, occlusion handling, and mental rotation—skills intuitive for humans but difficult for current AI systems. The system employs a procedural generation pipeline with constraint-based difficulty control, automated correctness verification, and human-in-the-loop validation to ensure scalability, robustness, and adaptability. Evaluation on a corresponding benchmark, **Spatial-CAPTCHA-Bench**, demonstrates that humans vastly outperform 10 state-of-the-art MLLMs, with the best model achieving only 31.0\% Pass@1 accuracy. Result comparison with Google reCAPTCHA further confirms the effectiveness of Spatial CAPTCHA as both a security mechanism and a diagnostic tool for spatial reasoning in AI.

Real-world Table–Text question answering (QA) tasks require models that can reason across long text and source tables, traversing multiple hops and executing complex operations such as aggregation. Yet existing benchmarks are small, manually curated—and therefore error-prone—and contain shallow questions that seldom demand more than two hops or invoke aggregations, grouping, or other advanced analytical operations expressible in natural-language queries. We present SPARTA, an end-to-end construction framework that automatically generates large-scale Table–Text QA benchmarks with lightweight human validation, requiring only one quarter of the annotation time of HybridQA. The framework first constructs a reference fact database by enriching each source table with grounding tables whose tuples are atomic facts automatically extracted from the accompanying unstructured passages, then synthesizes nested queries whose number of nested predicates matches the desired hop count. To ensure that every SQL statement is executable and that its verbalization yields a fluent, human-sounding question, we propose two novel techniques: provenance-based refinement, which rewrites any syntactically valid query that returns a non-empty result, and realistic-structure enforcement, which confines generation to post-order traversals of the query graph. The resulting pipeline produces thousands of high-fidelity question–answer pairs covering aggregations, grouping, and deep multi-hop reasoning across text and tables. On SPARTA, state-of-the-art models that reach over 70 F1 on HybridQA or over 50 F1 on OTT-QA drop by more than 30 F1 points, exposing fundamental weaknesses in current cross-modal reasoning. We will release the benchmark, construction code, and baseline results to spur progress toward robust, realistic Table–Text QA models.

Search has emerged as core infrastructure for LLM-based agents and is widely viewed as critical on the path toward more general intelligence. Finance is a particularly demanding proving ground: analysts routinely conduct complex, multi-step searches over time-sensitive, domain-specific data, making it ideal for assessing both search proficiency and knowledge-grounded reasoning. Yet no existing open financial datasets evaluate data searching capability of end-to-end agents, largely because constructing realistic, complicated tasks requires deep financial expertise and time-sensitive data is hard to evaluate. We present FinSearchComp, the first fully open-source agent benchmark for realistic, open-domain financial search and reasoning. FinSearchComp comprises three tasks, Time-Sensitive Data Fetching, Simple Historical Lookup, and Complex Historical Investigation, closely reproducing real-world financial analyst workflows. To ensure difficulty and reliability, we engage $70$ professional financial experts for annotation and implement a rigorous multi-stage quality-assurance pipeline. The benchmark includes $635$ questions spanning global and Greater China markets, and we evaluate $21$ models (products) on it. Grok 4 (web) tops the global subset, approaching expert-level accuracy. DouBao (web) leads on the Greater China subset. Experimental analyses show that equipping agents with web search and financial plugins substantially improves results on FinSearchComp, and the country origin of models and tools impact performance significantly. By aligning with realistic analyst tasks and providing end-to-end evaluation, FinSearchComp offers a professional, high-difficulty testbed for complex financial search and reasoning.

Reinforcement learning with verifiable rewards has significantly advanced reasoning with large language models (LLMs) in domains such as mathematics and logic. However, verifiable signals provide only coarse-grained or binary correctness feedback. This limitation results in inefficiencies like overly verbose or repetitive reasoning. Existing length-based solutions (e.g., length penalty) compromise accuracy. To address this deficiency, we introduce **self-aligned reward (SAR)**, a generic, universally applicable self-guided signal that complements verifiable rewards to enhance both reasoning accuracy and efficiency in RL. Specifically, SAR is defined as the relative perplexity difference between an answer conditioned on the query and the standalone answer, thereby favoring responses that are concise and query-specific. Quantitative analysis reveals that SAR reliably judges answer quality: concise, correct answers score higher than redundant ones, and partially correct answers score higher than entirely incorrect ones. Evaluation on 4 different models across 7 benchmarks shows that integrating SAR with prevalent RL algorithms like PPO and GRPO reduces answer length by 30%, while improving accuracy by 4%. Our analysis also shows that SAR generalizes well to out-of-domain tasks and achieves a Pareto-optimal frontier between correctness and efficiency compared to state-of-the-art baselines. We also show that SAR shortens unnecessary elaboration while preserving advanced reasoning behaviors. These results highlight the promise of self-aligned reward as a fine-grained complement to verifiable rewards, paving the way for efficient and effective LLM training. All of our code implementations and data are publicly available at GitHub.

Vision-language navigation (VLN) requires intelligent agents to navigate environments by interpreting linguistic instructions alongside visual observations, serving as a cornerstone task in Embodied AI. Current VLN research for unmanned aerial vehicles (UAVs) relies on detailed, pre-specified instructions to guide the UAV along predetermined routes. However, real-world outdoor exploration typically occurs in unknown environments where detailed navigation instructions are unavailable. Instead, only coarse-grained positional or directional guidance can be provided, requiring UAVs to autonomously navigate through continuous planning and obstacle avoidance. To bridge this gap, we propose AutoFly, an end-to-end Vision-Language-Action (VLA) model for autonomous UAV navigation. AutoFly incorporates a pseudo-depth encoder that derives depth-aware features from RGB inputs to enhance spatial reasoning, coupled with a progressive two-stage training strategy that effectively aligns visual, depth, and linguistic representations with action policies. Moreover, existing VLN datasets have fundamental limitations for real-world autonomous navigation, stemming from their heavy reliance on explicit instruction-following over autonomous decision-making and insufficient real-world data. To address these issues, we construct a novel autonomous navigation dataset that shifts the paradigm from instruction-following to autonomous behavior modeling through: (1) trajectory collection emphasizing continuous obstacle avoidance, autonomous planning, and recognition workflows; (2) comprehensive real-world data integration. Experimental results demonstrate that AutoFly achieves a 3.9\% higher success rate compared to state-of-the-art VLA baselines, with consistent performance across simulated and real environments.

Unified Multimodal Large Language Models (U-MLLMs) have garnered considerable interest for their ability to seamlessly integrate generation and comprehension tasks. However, existing research lacks a unified evaluation standard, often relying on isolated benchmarks to assess these capabilities. Moreover, current work highlights the potential of ``mixed-modality generation capabilities'' through case studies—such as generating auxiliary lines in images to solve geometric problems, or reasoning through a problem before generating a corresponding image. Despite this, there is no standardized benchmark to assess models on such unified tasks. To address this gap, we introduce MME-Unify, also termed as MME-U, the first open and reproducible benchmark designed to evaluate multimodal comprehension, generation, and mixed-modality generation capabilities. For comprehension and generation tasks, we curate a diverse set of tasks from 12 datasets, aligning their formats and metrics to develop a standardized evaluation framework. For unified tasks, we design five subtasks to rigorously assess how models’ understanding and generation capabilities can mutually enhance each other. Evaluation of 12 U-MLLMs, including Janus-Pro, EMU3, and Gemini2-Flash, reveals significant room for improvement, particularly in areas such as instruction following and image generation quality.

Fake news undermines societal trust and decision-making across politics, economics, health, and international relations, and in extreme cases threatens human lives and societal safety. Because fake news reflects region-specific political, social, and cultural contexts and is expressed in language, evaluating the risks of large language models (LLMs) requires a multi-lingual and regional perspective. Malicious users can bypass safeguards through jailbreak attacks, inducing LLMs to generate fake news. However, no benchmark currently exists to systematically assess attack resilience across languages and regions. Here, we propose JailNewsBench, the first benchmark for evaluating LLM robustness against jailbreak-induced fake news generation. JailNewsBench spans 34 regions and 22 languages, covering 8 evaluation sub-metrics through LLM-as-a-Judge and 5 jailbreak attacks, with approximately 300k instances. Our evaluation of 9 LLMs reveals that the maximum attack success rate reached 86.3% and the maximum harmfulness score was 3.5 out of 5. Notably, for English and U.S.-related topics, the defensive performance of typical multilingual LLMs was significantly higher than for other regions, highlighting substantial imbalances in safety across languages and regions. In addition, our analysis shows that coverage of fake news in existing safety datasets is limited and less well defended than major categories such as toxicity and social bias.

Many real-world data science tasks involve complex web-based interactions: finding appropriate data available on the internet, synthesizing multimodal data from different locations, and producing summarized analyses. Existing web benchmarks often focus on simplistic interactions and often do not require diverse tool-using capabilities. Conversely, traditional data science benchmarks typically concentrate on static, highly structured datasets and do not assess end-to-end workflows that encompass data acquisition, cleaning, analysis, and insight generation. In response, we introduce WebDS, the first end-to-end web-based data science benchmark. It comprises 870 web-based data science tasks across 29 diverse websites from structured government data portals to unstructured news media, challenging agents to perform complex, multi-step, tool-based operations, across heterogeneous data formats, to better reflect the realities of modern data analytics. Evaluations of current SOTA LLM agents indicate significant performance gaps in accomplishing these tasks. For instance, Browser Use, which accomplishes 80% of tasks on Web Voyager, completes only 15% of tasks in WebDS, which our analysis suggests is due to new failure modes like poor information grounding, repetitive behavior and shortcut-taking that agents performing WebDS' tasks display. By contrast, humans achieve around 90% accuracy, highlighting a substantial gap between current agents and human performance. By providing a more robust and realistic testing ground, WebDS sets the stage for significant advances in the development of practically useful LLM-based data science.

Large language models (LLMs) are evolving into agentic systems that reason, plan, and operate external tools. The Model Context Protocol (MCP) is a key enabler of this transition, offering a standardized interface for connecting LLMs with heterogeneous tools and services. Yet MCP's openness and multi-server workflows introduce new safety risks that existing benchmarks fail to capture, as they focus on isolated attacks or lack real-world coverage. We present \textbf{MCP-SafetyBench}, a comprehensive benchmark built on real MCP servers that supports realistic multi-turn evaluation across five domains—browser automation, financial analysis, location navigation, repository management, and web search. It incorporates a unified taxonomy of 20 MCP attack types spanning server, host, and user sides, and includes tasks requiring multi-step reasoning and cross-server coordination under uncertainty. Using MCP-SafetyBench, we systematically evaluate leading open- and closed-source LLMs, revealing large disparities in safety performance and escalating vulnerabilities as task horizons and server interactions grow. Our results highlight the urgent need for stronger defenses and establish MCP-SafetyBench as a foundation for diagnosing and mitigating safety risks in real-world MCP deployments.Our benchmark is available at https://anonymous.4open.science/r/MCP-SafetyBench-5738.

Evaluating open-ended outputs of Multimodal Large Language Models has become a bottleneck as model capabilities, task diversity, and modality rapidly expand. Existing ``MLLM-as-a-Judge'' evaluators, though promising, remain constrained to specific tasks and aspects (i.e., specific evaluation criteria such as fluency for text and image quality for images). In this paper, we argue that, on one hand, based on the interconnected nature of criteria, learning specific aspects can generalize to unseen aspects; on the other hand, jointly learning to assess multiple visual criteria and tasks may foster a synergistic effect. To this end, we propose UFEval, the first unified fine-grained evaluator with task and aspect generalization for four evaluation tasks --- Natural Language Generation, Image Understanding, Image Generation, and Interleaved Text-and-Image Generation. However, training such a unified evaluator is hindered by the lack of a large-scale, multi-modal, and aspect-level resource. To address this gap, we introduce FRABench, a comprehensive fine-grained evaluation dataset. Specifically, (1) We first construct a hierarchical aspect taxonomy encompassing 112 distinct aspects across the aforementioned four tasks. (2) Based on this taxonomy, we create FRABench, comprising 60.4k pairwise samples with 325k evaluation labels obtained from a combination of human and GPT-4o annotations. (3) Finally, leveraging FRABench, we develop UFEval, a unified fine-grained evaluator. Experiments show that learning on specific aspects enables UFEval to generalize to unseen aspects, and joint learning to assess diverse visual tasks and aspects can lead to substantial mutual benefits.

Significant progress has been made in photo-realistic scene reconstruction over recent years. Various disparate efforts have enabled capabilities such as multi-appearance or large-scale reconstruction from images acquired by consumer-grade cameras. How far away are we from digitally replicating the real world in 4D? So far, there appears to be a lack of well-designed dataset that can evaluate the holistic progress on large-scale scene reconstruction. We introduce a collection of imagery on a campus, acquired at different seasons, times of day, from multiple elevations, views, and at scale. To estimate many camera poses over such a large area and across elevations, we apply a semi-automated calibration pipeline to eliminate visual ambiguities and avoid excessive matching, then visually verify all calibration results to ensure accuracy. Finally, we benchmark various algorithms for automatic calibration and dense reconstruction on our dataset, named ULTRA-360, and demonstrate numerous potential areas to improve upon, e.g., balancing sensitivity and specificity in feature matching, densification and floaters in dense reconstruction, multi-appearance overfitting, etc. We believe ULTRA-360 can serve as the benchmark that reflect realistic challenges in an end-to-end scene-reconstruction pipeline.