ICLR 2026 论文列表

Pass@$k$ is widely used to report performance for LLM reasoning, but it often yields unstable, misleading rankings, especially when the number of trials (samples) is limited and compute is constrained. We present a principled Bayesian evaluation framework that replaces Pass@$k$ and average accuracy over $N$ trials (avg@$N$) with posterior estimates of a model's underlying success probability and credible intervals, yielding stable rankings and a transparent decision rule for differences. Evaluation outcomes are modeled as categorical (not just 0/1) with a Dirichlet prior, giving closed-form expressions for the posterior mean and uncertainty of any weighted rubric and enabling the use of prior evidence when appropriate. Theoretically, under a uniform prior, the Bayesian posterior mean is order-equivalent to average accuracy (Pass@$1$), explaining its empirical robustness while adding principled uncertainty. Empirically, in simulations with known ground-truth success rates and on AIME'24/'25, HMMT, and BrUMO, the Bayesian/avg procedure achieves faster convergence and greater rank stability than Pass@$k$ and recent variants, enabling reliable comparisons at far smaller sample counts. The framework clarifies when observed gaps are statistically meaningful (non-overlapping credible intervals) versus noise, and it naturally extends to graded, rubric-based evaluations. Together, these results recommend replacing Pass@$k$ for LLM evaluation and ranking with a posterior-based, compute-efficient protocol that unifies binary and non-binary evaluation while making uncertainty explicit.

The Chain of Action-Planning Thoughts (CoaT) paradigm has been shown to improve the reasoning performance of VLM-based mobile agents in GUI tasks. However, the scarcity of diverse CoaT trajectories limits the expressiveness and generalization ability of such agents. While self-training is commonly employed to address data scarcity, existing approaches either overlook the correctness of intermediate reasoning steps or depend on expensive process-level annotations to construct process reward models (PRM). To address the above problems, we propose an Iterative Preference Learning (IPL) that constructs a CoaT-tree through interative sampling, scores leaf nodes using rule-based reward, and backpropagates feedback to derive Thinking-level Direct Preference Optimization (T-DPO) pairs. To prevent overfitting during warm-up supervised fine-tuning, we further introduce a three-stage instruction evolution, which leverages GPT-4o to generate diverse Q&A pairs based on real mobile UI screenshots, enhancing both generality and layout understanding. Experiments on three standard Mobile GUI-agent benchmarks demonstrate that our agent MobileIPL outperforms strong baselines, including continual pretraining models such as OS-ATLAS and UI-TARS. It achieves state-of-the-art performance across three standard Mobile GUI-Agents benchmarks and shows strong generalization to out-of-domain scenarios.

Rotary Position Embeddings (RoPE) are widely adopted in LLMs, and it is commonly believed that larger base frequencies $\theta$ yield better long-context performance. In this paper, we show that a high-norm RoPE dimension, referred to as the “frequency band,” consistently emerges across multiple models, and we focus on this band to reveal the trade-offs inherent in RoPE. We find that replacing the RoPE dimensions below the frequency band with NoPE during inference has little effect on performance, indicating that these lower-frequency dimensions are only weakly utilized. We further find that the location of the frequency band depends on the RoPE base $\theta$ and the training sequence length. Moreover, the band forms early during pre-training and persists even after context extension via position interpolation. Notably, we show that aligning $\theta$ with the training length shifts the band toward lower frequencies and improves extrapolation, whereas increasing $\theta$ enhances interpolation but reduces extrapolation, revealing a clear trade-off between interpolation and extrapolation. We believe this work is a step toward a sharper understanding of positional embeddings in LLMs, with falsifiable diagnostics and practical guidance for choosing $\theta$ that support scaling to longer contexts.

Unified multimodal Large Language Models (MLLMs) hold great promise for seamlessly integrating understanding and generation. However, monolithic autoregressive architectures, despite their elegance and conversational fluency, suffer from a fundamental semantic–structural conflict: optimizing for low-level reconstructability in generation leads to catastrophic forgetting of high-level semantic understanding. We present ORION, a unified framework that resolves this conflict through Decoupling and Alignment. A non-linear vision head decouples structural pressures from shared representations, while a novel Representation Consistency Loss explicitly aligns semantics during generation. Together with a curated progressive training recipe and high-quality multimodal data, our method enables balanced optimization of both capabilities. Built purely on a monolithic autoregressive backbone without task-specific separate parameters, ORION achieves performance on par with or exceeding recent state-of-the-art unified models that rely on more complex designs. These results validate monolithic autoregression as a simple, effective, and competitive path toward truly integrated multimodal intelligence.

We introduce M3-Agent, a novel multimodal agent framework equipped with long-term memory. Like humans, M3-Agent can process real-time visual and auditory inputs to build and update episodic and semantic memories, gradually accumulating world knowledge. Its memory is organized in an entity-centric, multimodal manner, enabling deeper and more consistent understanding of the environment. Given an instruction, M3-Agent autonomously performs multi-turn reasoning and retrieves relevant memories to complete tasks. To evaluate memory effectiveness and memory-based reasoning in multimodal agents, we develop M3-Bench, a long-video question answering benchmark comprising 100 newly recorded robot-perspective videos (M3-Bench-robot) and 920 diverse web-sourced videos (M3-Bench-web). We annotate QA pairs designed to test capabilities essential for agent applications, such as person understanding, general knowledge extraction, and cross-modal reasoning. Experimental results show that M3-Agent, trained via reinforcement learning, outperforms the strongest baseline, a prompting agent using Gemini-1.5-pro and GPT-4o, achieving 6.7%, 7.7%, and 5.3% higher accuracy on M3-Bench-robot, M3-Bench-web and VideoMME-long, respectively. Our work advances multimodal agents toward more human-like long-term memory and provides insights for their practical design. Models, datasets and code are available at https://github.com/ByteDance-Seed/m3-agent.

Models are susceptible to adversarially out-of-distribution (OOD) data despite large training-compute investments into their robustification. Zaremba et al. (2025) make progress on this problem at test time, showing LLM reasoning improves satisfaction of model specifications designed to thwart attacks, resulting in a correlation between reasoning effort and robustness to jailbreaks. However, this benefit of test compute fades when attackers are given access to gradients or multimodal inputs. We address this gap, clarifying that inference-compute offers benefits even in such cases. Our approach argues that compositional generalization, through which OOD data is understandable via its in-distribution (ID) components, enables adherence to defensive specifications on adversarially OOD inputs. Namely, we posit the Robustness from Inference Compute Hypothesis (RICH): inference-compute defenses profit as the model's training data better reflects the attacked data’s components. We empirically support this hypothesis across vision language model and attack types, finding robustness gains from test-time compute if specification following on OOD data is unlocked by compositional generalization. For example, InternVL 3.5 gpt-oss 20B gains little robustness when its test compute is scaled, but such scaling adds significant robustness if we first robustify its vision encoder. This correlation of inference-compute's robustness benefit with base model robustness is the rich-get-richer dynamic of the RICH: attacked data components are more ID for robustified models, aiding compositional generalization to OOD data. Thus, we advise layering train-time and test-time defenses to obtain their synergistic benefit.

Diffusion policies for visuomotor robot manipulation tasks achieve remarkable dexterity and robustness while only training on a small number of task demonstrations. However, the reason for this performance remains a mystery. In this paper, we offer a surprising hypothesis: diffusion policies essentially memorize an action lookup table---\emph{and this is beneficial}. We posit that, at runtime, diffusion policies find the closest training image to the test image in a latent space, and recall the associated training action (i.e. action chunk), offering reactivity without the need for action generalization. This is effective in the sparse data regime, where there is not enough data density for the model to learn action generalization. We support this claim with systematic empirical evidence, showing that even when conditioned on highly out of distribution (OOD) images, Diffusion Policy still outputs an action chunk from the training data. We evaluate and compare three representative policy families on the same data set: Diffusion Policy, Action Chunking with Transformers (ACT), and GR00T, a pre-trained generalist Vision-Language-Action (VLA) model. We show that Diffusion Policy gives strong action memorization giving surprising robustness in OOD regimes, ACT shows action interpolation with poor robustness in OOD regimes, and GR00T (benefiting from substantial pre-training) shows both action interpolation and OOD robustness. As a simple alternative to Diffusion Policy, we introduce the Action Lookup Table (ALT) policy, showing that an explicit lookup table policy can perform comparably in this low data regime. Despite its simplicity, ALT attains Diffusion Policy–level performance while also providing faster inference and explicit OOD detection via latent-distance thresholds. These results reframe diffusion policies for robot manipulation as reactive memory retrieval under data sparsity, and provide practical tools for interpreting, evaluating, and monitoring such policies. More information can be found at: \url{https://stanfordmsl.github.io/alt/}.

Large language and vision-language models have inspired end-to-end vision-language-action (VLA) systems in robotics, yet existing robot datasets remain costly, embodiment-specific, and insufficient, limiting robustness and generalization. Recent approaches address this by adopting a plan-then-execute paradigm, where high-level plans are generated before translating into low-level actions, but their success depends on fine-grained intermediate supervision that current datasets lack. To fill this gap, we present the RoboInter Manipulation Suite, a unified resource for data, benchmarking, and modeling of intermediate representations. It includes RoboInter-Tool, a lightweight GUI for semi-automatic per-frame annotation of embodied videos, and RoboInter-Data, a human-verified dataset with over 200k episodes across 571 diverse scenes, offering dense per-frame alignment across more than nine intermediate categories and surpassing prior work in both scale and quality. Building on this foundation, RoboInter-VQA introduces 8 spatial and 20 temporal embodied QA categories to benchmark and enhance the embodied capabilities of current large vision-language models, while RoboInter-VLA provides a flexible plan-then-execute framework with modular and end-to-end variants that link planning to execution. Together, these contributions establish RoboInter Manipulation Suite as a foundation for advancing generalizable and robust robotic learning through fine-grained intermediate supervision.

Supervised fine-tuning (SFT) relies critically on selecting training data that most benefits model's downstream performance. Gradient-based data selection methods such as TracIn and Influence Functions leverage influence to identify useful samples, but their computational cost scales poorly, making them impractical for multi-billion-parameter large language models (LLMs). A common alternative is to use off-the-shelf smaller models as proxies, but they remain suboptimal since their learning dynamics are unclear, their sizes cannot be flexibly adjusted, and they cannot be further aligned with the target model in terms of gradient-based influence estimation. To address these challenges, we introduce IProX, a two-stage framework that derives influence-preserving proxies directly from the target model. It first applies a low-rank compression stage to preserve influence information of the target model, and then an aligning stage to align both model gradients and logits, thereby constructing proxies that flexibly control computational cost while retaining the target model’s influence. Experimental results across diverse LLM families and evaluation tasks show that IProX consistently outperforms off-the-shelf proxies and baseline methods. On Qwen3-4B, a 1.5B proxy constructed with IProX achieves stronger performance than the larger 1.7B off-the-shelf proxy. Notably, on Llama3.2, IProX achieves better performance than baselines while reducing computational cost by more than half relative to the full 3B model. These results show that IProX provides effective influence-preserving proxies, making gradient-based data selection more scalable for LLMs.

Generalist robot policies, or robotic foundation models, hold immense potential to enable flexible, general-purpose and dexterous robotic systems. Despite their advancements, our empirical experiments reveal that existing robot policies are prone to learning spurious correlations from pre-training trajectories, adversely affecting their generalization capabilities during inference. To tackle this, we propose a novel Policy Contrastive Decoding (PCD) approach, which redirects the robot policy’s focus toward object-relevant visual clues by contrasting action probability distributions derived from original and object-masked visual inputs. As a training-free method, our PCD can be used as a plugin to improve different types of robot policies without needing to finetune or access model weights. We conduct extensive experiments on top of three open-source robot policies, including the autoregressive policy OpenVLA and the diffusion-based policies Octo and Pi-0. The obtained results in both simulation and real-world environments prove PCD’s flexibility and effectiveness, e.g., PCD enhances the state-of-the-art policy $\pi_0$ by 8.9% in the simulation environment and by 108% in the real-world environment. Our code is publicly available at: https://github.com/pcd-robot/PCD.

Quantization significantly accelerates inference in large language models (LLMs) by replacing original high-precision matrices with low-precision counterparts. Recent advances in weight-activation quantization have primarily focused on mapping both weights and activations to the INT4 format. Although the new FP4 Tensor Cores in NVIDIA’s Blackwell architecture offer up to 4$\times$ speedup over FP16, existing INT4-based kernels fail to fully exploit this capability due to mismatched data formats. To bridge this gap, we propose MicroMix, a co-designed mixed-precision quantization algorithm and GEMM kernel based on Microscaling (MX) data formats. Tailored for the Blackwell architecture, the MicroMix kernel supports arbitrary combinations of MXFP4, MXFP6, and MXFP8 channels, and produces BFloat16 outputs. To achieve a favorable trade-off between accuracy and efficiency for each linear layer, we introduce quantization thresholds that identify activation elements where lower-precision formats (MXFP4 or MXFP6) incur excessive quantization error. Our algorithm selectively allocates higher-precision channels to preserve accuracy while maintaining compute efficiency. On the Llama and Qwen model families, MicroMix achieves near-FP16 performance across diverse downstream tasks with an average precision of 5 bits. In particular, Qwen2.5-32B-Base and Coder exhibit lossless accuracy on zero-shot, code generation, and mathematical reasoning benchmarks. In addition, on RTX 5070Ti laptop and RTX 5090 GPUs, our kernel achieves 2.29-3.38$\times$ acceleration compared to TensorRT-FP16. Our code is available at \url{https://github.com/lwy2020/MicroMix}.

Infographic charts are a powerful medium for communicating abstract data by combining visual elements (e.g., charts, images) with textual information. However, their visual and structural richness poses challenges for large vision-language models (LVLMs), which are typically trained on plain charts. To bridge this gap, we introduce ChartGalaxy, a million-scale dataset designed to advance the understanding and generation of infographic charts. The dataset is constructed through an inductive process that identifies 75 chart types, 440 chart variations, and 68 layout templates from real infographic charts and uses them to create synthetic ones programmatically. We showcase the utility of this dataset through: 1) improving infographic chart understanding via fine-tuning, 2) benchmarking code generation for infographic charts, and 3) enabling example-based infographic chart generation. By capturing the visual and structural complexity of real design, ChartGalaxy provides a useful resource for enhancing multimodal reasoning and generation in LVLMs.

Safety evaluation of multimodal foundation models often treats vision and language inputs separately, missing risks from joint interpretation where benign content becomes harmful in combination. Existing approaches also fail to distinguish clearly unsafe content from borderline cases, leading to problematic over-blocking or under-refusal of genuinely harmful content. We present Vision Language Safety Understanding (VLSU), a comprehensive framework to systematically evaluate multimodal safety through fine-grained severity classification and combinatorial analysis across 17 distinct safety patterns. Using a multi-stage pipeline with real-world images and human annotation, we construct a large-scale benchmark of 8,187 samples spanning 15 harm categories. Our evaluation of eleven state-of-the-art models reveals systematic joint understanding failures: while models achieve 90\%+ accuracy on clear unimodal safety signals, performance degrades substantially to 20-55\% when joint image-text reasoning is required to determine the safety label. Most critically, 34\% of errors in joint image-text safety classification occur despite correct classification of the individual modalities, further demonstrating absent compositional reasoning capabilities. Additionally, we find that models struggle to balance refusing unsafe content while still responding to borderline cases that deserve engagement. For example, we find that instruction framing can reduce the over-blocking rate on borderline content from 62.4\% to 10.4\% in Gemini-1.5, but only at the cost of under-refusing on unsafe content with refusal rate dropping from 90.8\% to 53.9\%. Overall, our framework exposes weaknesses in joint image-text understanding and alignment gaps in current models, and provides a critical test bed to enable the next milestones in research on robust vision–language safety.

Recent advances in Vision-Language Models (VLMs) have propelled embodied agents by enabling direct perception, reasoning, and planning task-oriented actions from visual inputs. However, such vision-driven embodied agents open a new attack surface: visual backdoor attacks, where the agent behaves normally until a visual trigger appears in the scene, then persistently executes an attacker-specified multi-step policy. We introduce BEAT, the first framework to inject such visual backdoors into VLM-based embodied agents using objects in the environments as triggers. Unlike textual triggers, object triggers exhibit wide variation across viewpoints and lighting, making them difficult to implant reliably. BEAT addresses this challenge by (1) constructing a training set that spans diverse scenes, tasks, and trigger placements to expose agents to trigger variability, and (2) introducing a two-stage training scheme that first applies supervised fine-tuning (SFT) and then our novel Contrastive Trigger Learning (CTL). CTL formulates trigger discrimination as preference learning between trigger-present and trigger-free inputs, explicitly sharpening the decision boundaries to ensure precise backdoor activation. Across various embodied agent benchmarks and VLMs, BEAT achieves attack success rates up to 80\%, while maintaining strong benign task performance, and generalizes reliably to out-of-distribution trigger placements. Notably, compared to naive SFT, CTL boosts backdoor activation accuracy up to 39\% under limited backdoor data. These findings expose a critical yet unexplored security risk in VLM-based embodied agents, underscoring the need for robust defenses before real-world deployment.

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. Existing simulation benchmarks are similarly limited, as they train and test policies within the same synthetic domains and cannot assess models trained primarily on real-world demonstrations, which is the dominant paradigm for today’s vision-language-action (VLA) models. 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. In this paper, we introduce 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.

Urban development impacts over half of the global population, making human-centered understanding of its structural and perceptual changes essential for smart city planning. While Multimodal Large Language Models (MLLMs) have shown remarkable capabilities across various domains, existing benchmarks that explore their performance in urban environments remain limited, lacking systematic exploration of temporal evolution and subjective perception of urban environment that aligns with human perception. To address these limitations, we propose UrbanFeel, a comprehensive benchmark designed to evaluate the performance of MLLMs in urban development understanding and subjective environmental perception. UrbanFeel comprises 14.3K carefully constructed visual questions spanning three cognitively progressive dimensions: Static Scene Perception, Temporal Change Perception, and Subjective Environmental Perception. We collect multi-temporal single-view and panoramic street-view images from 11 representative cities worldwide, and generate high-quality question-answer pairs through a hybrid pipeline of spatial clustering, rule-based generation, model-assisted prompting, and manual annotation. Through extensive evaluation of 20 state-of-the-art MLLMs, we observe that Gemini-2.5 Pro achieves the best overall performance, with its accuracy approaching human expert levels and narrowing the average gap to just 1.5%. Most models perform well on tasks grounded in scene understanding. In particular, some models even surpass human annotators in pixel-level change detection. However, performance drops notably in tasks requiring temporal reasoning over urban development. Additionally, in the subjective perception dimension, several models reach human-level or even higher consistency in evaluating dimension such as beautiful and safety. Our results suggest that MLLMs are demonstrating rudimentary emotion understanding capabilities. Our UrbanFeel benchmark will be made publicly available.

While most autoregressive LLMs are constrained to one-by-one decoding, diffusion LLMs (dLLMs) have attracted growing interest for their potential to dramatically accelerate inference through parallel decoding. Despite this promise, the conditional independence assumption in dLLMs causes parallel decoding to ignore token dependencies, inevitably degrading generation quality when these dependencies are strong. However, existing works largely overlook these inherent challenges, and evaluations on standard benchmarks (e.g., math and coding) are not sufficient to capture the quality degradation caused by parallel decoding. To address this gap, we first provide an information-theoretic analysis of parallel decoding. We then conduct case studies on analytically tractable synthetic list operations from both data distribution and decoding strategy perspectives, offering quantitative insights that highlight the fundamental limitations of parallel decoding. Building on these insights, we propose **ParallelBench**, the first benchmark specifically designed for dLLMs, featuring realistic tasks that are trivial for humans and autoregressive LLMs yet exceptionally challenging for dLLMs under parallel decoding. Using ParallelBench, we systematically analyze both dLLMs and autoregressive LLMs, revealing that: (i) dLLMs under parallel decoding can suffer dramatic quality degradation in real-world scenarios, and (ii) current parallel decoding strategies struggle to adapt their degree of parallelism based on task difficulty, thus failing to achieve meaningful speedup without compromising quality. Our findings underscore the pressing need for innovative decoding methods that can overcome the current speed-quality trade-off. We are releasing our benchmark to help accelerate the development of truly efficient dLLMs.

Humans can imagine and manipulate visual images mentally, a capability known as \textit{spatial visualization}. While many multi-modal benchmarks assess reasoning on visible visual information, the ability to infer unseen relationships through spatial visualization remains insufficiently evaluated as a spatial skill. This reliance on publicly sourced problems from IQ tests or math competitions risks data contamination and compromises assessment reliability. To this end, we introduce \textbf{\textit{SpatialViz-Bench}}, a comprehensive multi-modal benchmark for \textit{spatial visualization} with \emph{12} tasks across \emph{4} sub-abilities, comprising \emph{1,180} programmatically generated problems, a scalable framework that allows for expansion to ensure fair and continuously reliable evaluations. Our evaluation of \emph{27} Multi-modal Large Language Models (MLLMs) reveals wide performance variations, demonstrates the benchmark's strong discriminative power, and uncovers counter-intuitive findings: Chain-of-Thought (CoT) prompting paradoxically degrades accuracy on open-source models. Through statistical and qualitative analysis of error types, SpatialViz-Bench demonstrates that state-of-the-art MLLMs exhibit deficiencies in \textit{spatial visualization} tasks, thereby addressing a significant lacuna in the field.

Multimodal foundation models, such as GPT-4o, have recently made remarkable progress, but it is not clear where exactly these models stand in terms of understanding vision. In this paper, we benchmark the performance of popular multimodal foundation models (GPT-4o, o4-mini, Gemini 1.5 Pro and Gemini 2.0 Flash, Claude 3.5 Sonnet, Qwen2-VL, Llama 3.2) on standard computer vision tasks (semantic segmentation, object detection, image classification, depth and surface normal prediction) and using established datasets (e.g., COCO, ImageNet and its variants, etc). The main challenges to performing this are: 1) most models are trained to output text and cannot natively express versatile domains, such as segments or 3D geometry, and 2) many leading models are proprietary and accessible only at an API level, i.e., there is no weight access to adapt them. We address these challenges by translating standard vision tasks into equivalent text-promptable and API-compatible tasks via prompt chaining to create a standardized benchmarking framework. We observe that 1) the models are not close to the state-of-the-art specialist models at any tasks, and 2) they perform semantic tasks notably better than geometric ones. However, 3) they are respectable generalists; this is remarkable as they are presumably trained on primarily image-text-based tasks. 4) While the prompt-chaining techniques affect performance, better models exhibit less sensitivity to prompt variations. 5) GPT-4o performs the best among non-reasoning models, securing the top position in 4 out of 6 tasks and 6) reasoning models, e.g. o3, show improvements in geometric tasks.