ICLR 2026 Papers

Vision-Language-Action (VLA) models have emerged as a popular paradigm for learning robot manipulation policies that can follow language instructions and generalize to novel scenarios. Recent works have begun to explore the incorporation of latent actions, abstract representations of motion between two frames, into VLA pre-training. In this paper, we introduce villa-X a novel Vision-Language-Latent-Action (ViLLA) framework that advances latent action modeling for learning generalizable robot manipulation policies. Our approach improves both how latent actions are learned and how they are incorporated into VLA pre-training. We demonstrate that villa-X can generate latent action plans in a zero-shot fashion, even for unseen embodiments and open-vocabulary symbolic understanding. This capability enables villa-X to achieve superior performance across diverse simulation tasks in SIMPLER and on two real-world robotic setups involving both gripper and dexterous hand manipulation. These results establish villa-X as a principled and scalable paradigm for learning generalizable robot manipulation policies. We believe it provides a strong foundation for future research.

Evaluating the abilities of large language models (LLMs) for tasks that require long-term memory and thus long-context reasoning, for example in conversational settings, is hampered by the existing benchmarks, which often lack narrative coherence, cover narrow domains, and only test simple recall-oriented tasks. This paper introduces a comprehensive solution to these challenges. First, we present a novel framework for automatically generating long (up to 10M tokens), coherent, and topically diverse conversations, accompanied by probing questions targeting a wide range of memory abilities. From this, we construct BEAM, a new benchmark comprising 100 conversations and 2,000 validated questions. Second, to enhance model performance, we propose LIGHT–a framework inspired by human cognition that equips LLMs with three complementary memory systems: a long-term episodic memory, a short-term working memory, and a scratchpad for accumulating salient facts. Our experiments on BEAM reveal that even LLMs with 1M token context windows (with and without retrieval-augmentation) struggle as dialogues lengthen. In contrast, LIGHT consistently improves performance across various models, achieving an average improvement of 3.5%–12.69% over the strongest baselines, depending on the backbone LLM. An ablation study further confirms the contribution of each memory component.

Recent advancements in gait recognition have significantly enhanced performance by treating silhouettes as either an unordered set or an ordered sequence. However, both set-based and sequence-based approaches exhibit notable limitations. Specifically, set-based methods tend to overlook short-range temporal context for individual frames, while sequence-based methods struggle to capture long-range temporal dependencies effectively. To address these challenges, we draw inspiration from human identification and propose a new perspective that conceptualizes human gait as a composition of individualized actions. Each action is represented by a series of frames, randomly selected from a continuous segment of the sequence, which we term a snippet. Fundamentally, the collection of snippets for a given sequence enables the incorporation of multi-scale temporal context, facilitating more comprehensive gait feature learning. Moreover, we introduce a non-trivial solution for snippet-based gait recognition, focusing on Snippet Sampling and Snippet Modeling as key components. Extensive experiments on four widely-used gait datasets validate the effectiveness of our proposed approach and, more importantly, highlight the potential of gait snippets. For instance, our method achieves the rank-1 accuracy of 77.5% on Gait3D and 81.7% on GREW using a 2D convolution-based backbone.

Despite rapid advances in code generation, current Large Language Models (LLMs) still lack an essential capability for reliable and verifiable code generation: compositional reasoning across multi-function programs. To explore this potential and important gap, we introduce DafnyCOMP, a benchmark designed to systematically evaluate LLMs on the generation of compositional specifications in Dafny. Unlike prior benchmarks that primarily target single-function annotation, DafnyCOMP focuses on programs composed of multiple interacting functions with necessary data dependencies, requiring LLMs to produce specifications that ensure correctness across component boundaries. Our benchmark comprises 300 automatically synthesized programs, each carefully constructed by combining 2–5 originally independent functions in a chain-based manner through LLM-driven synthesis. We evaluate LLMs from five leading research groups that represent the current frontier of reasoning-centric AI, including the GPT, Claude, Gemini, DeepSeek, and Qwen families. Our results reveal a striking dichotomy: while LLMs achieve both high syntax correctness (>99%) and moderate verification rates (>58%) in prior single-function benchmarks, they exhibit degraded syntax correctness (95.67%) and a catastrophic verification failure (3.69%) in DafnyCOMP's compositional tasks— a 92% performance gap. Even the most powerful LLM achieves only 7% verification at Pass@8, with most LLMs below 2%. Further analysis reveals that LLMs systematically fail at cross-functional reasoning through three primary failure modes: specification fragility (39.2%), implementation-proof misalignment (21.7%), and reasoning instability (14.1%). These failures clearly reveal the absence of compositional reasoning capabilities in current LLMs. DafnyCOMP thus establishes a diagnostic benchmark for tracking progress in verifiable code generation with LLMs, highlighting that the path from local to compositional verification remains largely uncharted.

Incomplete multi-view multi-label learning is fundamentally an information integration problem under simultaneous view and label incompleteness. We introduce Permutation-Consistent Variational Encoding framework (PCVE) with an information bottleneck strategy, which learns variational representations capable of aggregating shared semantics across views while remaining robust to incompleteness. PCVE formulates a principled objective that maximizes a variational evidence lower bound to retain task-relevant information, and introduces a permutation-consistent regularization to encourage distributional consistency among representations that encode the same target semantics from different views. This regularization acts as an information alignment mechanism that suppresses view-private redundancy and mitigates over-alignment, thereby improving both sufficiency and consistency of the learned representations. To address missing labels, PCVE further incorporates a masked multi-label learning objective that leverages available supervision while modeling label dependencies. Extensive experiments across diverse benchmarks and missing ratios demonstrate consistent gains over state-of-the-art methods in multi-label classification, while enabling reliable inference of missing views without explicit imputation. Analyses corroborate that the proposed information-theoretic formulation improves cross-view semantic cohesion and preserves discriminative capacity, underscoring the effectiveness and generality of PCVE for incomplete multi-view multi-label learning.

We present **THEMIS**, a novel multi-task benchmark designed to comprehensively evaluate Multimodal Large Language Models (MLLMs) on visual fraud reasoning within real-world academic scenarios. Compared to existing benchmarks, THEMIS introduces three major advancements. (1) **Real-world Scenarios & Complexity**: Our benchmark comprises over 4K questions spanning 7 scenarios, derived from authentic retracted-paper cases and carefully curated multimodal synthetic data. With 73.73% complex-texture images, THEMIS bridges the critical gap between existing benchmarks and the complexity of real-world academic fraud. (2) **Task Diversity & Granularity**: THEMIS systematically covers five challenging tasks and introduces 16 fine-grained manipulation operations. On average, each sample undergoes multiple stacked manipulation operations, with the diversity and difficulty of these manipulations demanding a high level of visual fraud reasoning from the models. (3) **Multi-dimensional Capability Evaluation**: We establish a mapping from fraud tasks to five core visual fraud reasoning capabilities, thereby enabling an evaluation that reveals the distinct strengths and specific weaknesses of different models across these core capabilities. Experiments on 11 leading MLLMs show that even the best-performing model still falls below the passing threshold, demonstrating that our benchmark presents a stringent test. We expect THEMIS to advance the development of MLLMs for complex, real-world fraud detection tasks. The data and code will be updated on url: https://anonymous.4open.science/r/themis1638.

Advancements in diffusion models have significantly improved video quality, directing attention to fine-grained controllability. However, many existing methods depend on fine-tuning large-scale video models for specific tasks, which becomes increasingly impractical as model sizes continue to grow. In this work, we present Frame Guidance, a training-free guidance for controllable video generation based on frame-level signals, such as keyframes, style reference images, sketches, or depth maps. By applying guidance to only a few selected frames, Frame Guidance can steer the generation of the entire video, resulting in a temporally coherent controlled video. To enable training-free guidance on large-scale video models, we propose a simple latent processing method that dramatically reduces memory usage, and apply a novel latent optimization strategy designed for globally coherent video generation. Frame Guidance enables effective control across diverse tasks, including keyframe guidance, stylization, and looping, without any training, and is compatible with any models. Experimental results show that Frame Guidance can produce high-quality controlled videos for a wide range of tasks and input signals.

Designing 3D ligands that bind to a given protein pocket with high affinity is a fundamental task in Structure-Based Drug Design (SBDD). However, the lack of synthesizability of 3D ligands has been hindering progress toward experimental validation; moreover, computationally evaluating synthesizability is a non-trivial task. In this paper, we first benchmark eight classical synthesizability metrics across 11 SBDD methods. The comparison reveals significant inconsistencies between these metrics, making them impractical and inaccurate criteria for guiding SBDD methods toward synthesizable drug design. Therefore, we propose a simple yet effective SE(3)-invariant \textit{\underline{SYN}thesizability \underline{C}lassifier} (SYNC) to enable better synthesizability estimation in SBDD, which demonstrates superior generalizability and speed compared to existing metrics on five curated datasets. Finally, with SYNC as a plug-and-play module, we establish a synthesizability classifier-driven SBDD paradigm through guided diffusion and Direct Preference Optimization, where highly synthesizable molecules are directly generated without compromising binding affinity. Extensive experiments also demonstrate the effectiveness of SYNC and the advantage of our paradigm in synthesizable SBDD. Code is available at \url{https://anonymous.4open.science/r/SYNC-C94D/}.

Context modeling is fundamental to LiDAR point cloud compression. Existing methods rely on computationally intensive 3D contexts, such as voxel and octree, which struggle to balance the compression efficiency and coding speed. In this work, we propose a neural LiDAR compressor based on 2D context models that simultaneously supports high-efficiency compression, fast coding, and universal geometry-intensity compression. The 2D context structure significantly reduces the coding latency. We further develop a comprehensive context model that integrates spatial latents, temporal references, and cross-modal camera context in the 2D domain to enhance the compression performance. Specifically, we first represent the point cloud as a range image and propose a multi-scale spatial context model to capture the intra-frame dependencies. Furthermore, we design an optical-flow-based temporal context model for inter-frame prediction. Moreover, we incorporate a deformable attention module and a context refinement strategy to predict LiDAR scans from camera images. In addition, we develop a backbone for joint geometry and intensity compression, which unifies the compression of both modalities while minimizing redundant computation. Experiments demonstrate significant improvements in both rate-distortion performance and coding speed. The code will be released upon the acceptance of the paper.

Large language models (LLMs) are typically trained to acquire behaviours from demonstrations or experience, yet much of their training data consists of symbolic descriptions: instructions, rules, and strategies that specify procedures without examples. We investigate whether LLMs can learn to execute such behaviours directly from their abstract description, a process we term *Programming by Backprop* (PBB). We study this phenomenon in two domains: first, using source code as a canonical form of procedural description by comparing models finetuned on algorithms versus execution examples; and second, extending beyond code to abstract grammar rules, testing whether models learn to generate compliant text. Our findings show that PBB can be elicited through targeted finetuning, demonstrating that LLMs can acquire new behaviours from symbolic descriptions, albeit not yet with full reliability. Once elicited, PBB enables models to internalise reusable procedural abstractions - generalising across inputs, executing procedures implicitly in a forward pass, and benefiting further from chain-of-thought reasoning. These results position PBB as a distinct pathway through which LLMs acquire behavioural skills from symbolic descriptions, with implications for both more efficient capability acquisition and aligning models through formal specifications rather than demonstrations alone.

Large Multimodal Models (LMMs) often rely on in-context learning (ICL) to perform new visual question answering (VQA) tasks with minimal supervision. However, ICL performance, especially in smaller LMMs, does not always improve monotonically when increasing the number of examples. We hypothesize that this happens because the LMM is overwhelmed by extraneous information in the image embeddings that is irrelevant to the downstream task. To address this, we propose a meta-learning approach that induces few-shot capabilities in LMMs through a fixed set of soft prompts distilled from task-relevant visual features, which are adapted at test time using a small number of examples. We facilitate this distillation through an attention-mapper module that can be easily integrated with any LMM architecture and is jointly learned with soft prompts. Evaluation on the VL-ICL Bench shows that our method successfully achieves task adaptation in low-data regimes with just a few gradient steps, outperforming ICL by 21.2%. Comparisons with parameter-efficient finetuning methods demonstrate that meta-learning further enhances this adaptation by 7.7% for various VQA tasks.

Representation alignment helps generation by distilling representations from a pretrained vision encoder to intermediate diffusion features. We investigate a fundamental question - `what aspect of the target representation matters for generation, its global information (measured by Imagenet1K accuracy) or its spatial structure (pairwise cosine similarity between patch tokens)''? Prevalent wisdom holds that stronger global performance leads to better generation as a target representation. To study this, we first perform a large-scale empirical analysis across 27 different vision encoders and different model scales. The results are surprising - spatial structure, rather than global performance drives the generation performance of a target representation. To further study this, we introduce two straightforward modifications, which specifically accentuate the transfer of spatial information. We replace the standard MLP projection layer in REPA with a simple convolution layer and introduce a spatial normalization layer for the external representation. Surprisingly, our simple method (implemented in <4 lines of code), termed iREPA, consistently improves convergence speed of REPA, across a diverse set of vision encoders, model sizes, and training variants (such as REPA-E and meanflow with REPA). Our work motivates revisiting the fundamental working mechanism of representational alignment and how it can be leveraged for improved training of generative models.

Standard representational similarity methods align each layer of a network to its best match in another independently, producing asymmetric results, lacking a global alignment score, and struggling with networks of different depths. These limitations arise from ignoring global activation structure and restricting mappings to rigid one-to-one layer correspondences. We propose Hierarchical Optimal Transport (HOT), a unified framework that jointly infers soft, globally consistent layer-to-layer couplings and neuron-level transport plans. HOT allows source neurons to distribute mass across multiple target layers while minimizing total transport cost under marginal constraints. This yields both a single alignment score for the entire network comparison and a soft transport plan that naturally handles depth mismatches through mass distribution. We evaluate HOT on vision models, large language models, and human visual cortex recordings. Across all domains, HOT matches or surpasses standard pairwise matching in alignment quality. Moreover, it reveals smooth, fine-grained hierarchical correspondences: early layers map to early layers, deeper layers maintain relative positions, and depth mismatches are resolved by distributing representations across multiple layers. These structured patterns emerge naturally from global optimization without being imposed, yet are absent in greedy layer-wise methods. HOT thus enables richer, more interpretable comparisons between representations, particularly when networks differ in architecture or depth. We further extend our method to a three-level HOT framework, providing a proof-of-concept alignment of two networks across their training trajectories and demonstrating that HOT uncovers checkpoint-wise correspondences missed by greedy layer-wise matching.

Rank aggregation has critical applications for developing AI agents, as well as for evaluating them. However, different methods can give rise to significantly different aggregate rankings, impacting these applications. Indeed, work in social choice and statistics has produced many rank aggregation methods, each with its desirable properties, but also with its limitations. Given this trade-off, how do we decide which aggregation rule to use, _i.e._, what is a good _rule picking rule (RPR)_? In this paper, we design a data-driven RPR that identifies the best method for each dataset without assuming a generative model. The principle behind our RPR is to maximize consistency if the data collection process was repeated. We show that our method satisfies several consistency-related axioms failed by a wide class of natural RPRs. While we prove that the computational problem of maximizing consistency is hard, we provide a sampling-based implementation that is efficient in practice. We run this implementation on known statistical models to experimentally demonstrate its desirable properties, as well as on real-world data where our method provides important insights into how to improve consistency.

Training computer-use agents requires massive amounts of GUI interaction data, but manually annotating action trajectories at scale is prohibitively expensive. We present VideoAgentTrek, a scalable pipeline that automatically mines training data from publicly available screen-recorded videos, eliminating the need for manual annotation. Our approach addresses a key challenge: raw videos contain implicit demonstrations but lack explicit action labels. To solve this, we develop Video2Action, an inverse dynamics module (IDM) with two components: (1) a video grounding model that detects and localizes GUI actions with precise temporal boundaries, and (2) an action-content recognizer that extracts structured parameters like click coordinates and typed text. Applied to 39,000 YouTube tutorial videos, our pipeline generates 1.52 million interaction steps. We leverage this data through continued pretraining followed by supervised fine-tuning. On OSWorld-Verified, our approach improves task success rates from 9.3% (SFT-only baseline) to 15.8%, a 70% relative improvement. On AgentNetBench, step accuracy increases from 64.1% to 69.3%. Our results demonstrate that passive internet videos can be transformed into high-quality supervision for computer-use agents, providing a scalable alternative to expensive manual annotation.

Long-context models (LCMs) have demonstrated great potential in processing long sequences, facilitating many real-world applications. The success of LCMs can be attributed to their ability to locate implicit critical information within the context for further prediction. However, recent research reveals that LCMs are often susceptible to contextual noise, i.e., irrelevant tokens, that can mislead model attention. In this paper, we conduct a fine-grained analysis of the context noise and propose an effective metric, the Integrated Gradient (IG) score, to detect and quantify the noise information within the context. Our findings reveal that even simple mitigation of detected context noise can substantially boost the model's attention on critical tokens and benefit subsequent predictions. Building on this insight, we propose Context Denoising Training (CDT), a straightforward yet effective training strategy that improves attention on critical tokens while reinforcing their influence on model predictions. Extensive experiments across four tasks, under both context window scaling and long-context alignment settings, demonstrate the superiority of CDT. Notably, when trained with CDT, an open-source 8B model can achieve performance (50.92) comparable to GPT-4o (51.00).

Writing GPU kernels is a challenging task and critical for AI systems' efficiency. It is also highly iterative: domain experts write code and improve performance through execution feedback. Moreover, it presents verifiable rewards like correctness and speedup, making it a natural environment to apply Reinforcement Learning (RL). To explicitly incorporate the iterative nature of this process into training, we develop a flexible multi-turn RL recipe that addresses unique challenges encountered in real-world settings, such as learning from long trajectories and effective reward attribution across turns. We present Kevin the Kernel Writer, the first model trained with multi-turn RL for CUDA kernel generation and optimization. In our evaluation setup, Kevin shows significant gains over its base model (QwQ-32B), improving correctness of generated kernels (in pure CUDA) from 56% to 82% and mean speedup from 0.53x to 1.10x of baseline (PyTorch Eager), and surpassing frontier models like o4-mini (0.78x). Finally, we study its behavior across test-time scaling axes: we found scaling serial refinement more beneficial than parallel sampling. In particular, when given more refinement turns, Kevin shows a higher rate of improvement.

Reward is critical to the evaluation and training of large language models (LLMs). However, existing rule-based or model-based reward methods struggle to generalize to GUI agents, where access to ground-truth trajectories or application databases is often unavailable, and static trajectory-based LLM-as-a-Judge approaches suffer from limited accuracy. To address these challenges, we propose ProRe, a proactive reward system that leverages a general-purpose reasoner and domain-specific evaluator agents (actors). The reasoner schedules targeted state probing tasks, which the evaluator agents then execute by actively interacting with the environment to collect additional observations. This enables the reasoner to assign more accurate and verifiable rewards to GUI agents. Empirical results on over 3K trajectories demonstrate that ProRe improves reward accuracy and F1 score by up to 5.3\% and 19.4\%, respectively. Furthermore, integrating ProRe with state-of-the-art policy agents yields a success rate improvement of up to 22.4\%.

Multimodal large language models are promising for clinical visual question answering tasks, but scaling to 3D imaging is hindered by high computational costs. Prior methods often rely on 2D slices or fixed-length token compression, disrupting volumetric continuity and obscuring subtle findings. We present Photon, a framework that represents 3D medical volumes with token sequences of variable length. Photon introduces instruction-conditioned token scheduling and surrogate gradient propagation to adaptively reduce tokens during both training and inference, which lowers computational cost while mitigating the attention dilution caused by redundant tokens. It incorporates a custom backpropagation rule with gradient restoration to enable differentiable optimization despite discrete token drop. To stabilize token compression and ensure reliable use of visual evidence, Photon further applies regularization objectives that mitigate language-only bias and improve reliability. Experiments on diverse medical visual question answering tasks show that Photon achieves state-of-the-art accuracy while reducing resource usage and accelerating both training and inference.