ICLR 2026 论文列表

Watermarking is a principled approach for tracing the provenance of large language model (LLM) outputs, but its deployment in practice is hindered by inference inefficiency. Speculative sampling accelerates inference, with efficiency improving as the acceptance rate between draft and target models increases. Yet recent work reveals a fundamental trade-off: higher watermark strength reduces acceptance, preventing their simultaneous achievement. We revisit this trade-off and show it is not absolute. We introduce a quantitative measure of watermark strength that governs statistical detectability and is maximized when tokens are deterministic functions of pseudorandom numbers. Using this measure, we fully characterize the trade-off as a constrained optimization problem and derive explicit Pareto curves for two existing watermarking schemes. Finally, we introduce a principled mechanism that injects pseudorandomness into draft-token acceptance, ensuring maximal watermark strength while maintaining speculative sampling efficiency. Experiments further show that this approach improves detectability without sacrificing efficiency. Our findings uncover a principle that unites speculative sampling and watermarking, paving the way for their efficient and practical deployment.

Large-scale video generative models, capable of creating realistic videos of diverse visual concepts, are strong candidates for general-purpose physical world simulators. However, their adherence to physical commonsense across real-world actions remains unclear (e.g., playing tennis, backflip). Existing benchmarks suffer from limitations such as limited size, lack of human evaluation, sim-to-real gaps, and absence of fine-grained physical rule analysis. To address this, we introduce VideoPhy-2, an action-centric dataset for evaluating physical commonsense in generated videos. We curate 4000 diverse and detailed prompts for video synthesis from modern generative models. We perform human evaluation that assesses semantic adherence, physical commonsense, and grounding of physical rules in the generated videos. Our findings reveal major shortcomings, with even the best model achieving only $47.7\%$ joint performance (i.e., high semantic and physical commonsense adherence) on the hard subset of VideoPhy-2. We find that the models particularly struggle with conservation laws like mass and momentum. Finally, we also train VideoPhy-2-AutoEval, an automatic evaluator for fast, reliable assessment on our dataset. Overall, VideoPhy-2 serves as a rigorous benchmark, exposing critical gaps in video generative models and guiding future research in physically-grounded video generation. We will release the dataset, videos, auto-rater model, and code in the camera-ready version.

The rapid growth of large language models (LLMs) has heightened the importance of post-training quantization (PTQ) for reducing memory and computation costs. Among PTQ methods, GPTQ has gained significant attention for its efficiency, enabling billion-scale LLMs to be quantized within a few GPU hours. However, GPTQ's assumption of layer-wise independence leads to severe accuracy drops in low-bit regimes. Recently, BoA improved upon GPTQ by incorporating inter-layer dependencies within attention modules, but its reliance on sequential quantization across all out-channels makes it substantially less efficient. In this paper, we propose TurboBoA, a new backpropagation-free PTQ algorithm that preserves the accuracy benefits of BoA while significantly accelerating the process. The proposed TurboBoA introduces three key innovations: (i) joint quantization of multiple out-channels with a closed-form error compensation rule, which reduces sequential bottlenecks and yields more than a three-fold speedup; (ii) a correction mechanism for errors propagated from preceding quantized layers; and (iii) adaptive grid computation with coordinate descent refinement to maintain alignment during iterative updates. Extensive experiments demonstrate that TurboBoA delivers substantial acceleration over BoA while consistently improving accuracy. When combined with outlier suppression techniques, it achieves state-of-the-art results in both weight-only and weight-activation quantization. The code will be available at https://github.com/SamsungLabs/TurboBoA.

Execution-based feedback like unit testing is widely used in the development of coding agents through test-time scaling (TTS) and reinforcement learning (RL). This paradigm requires scalable and reliable collection of unit test cases to provide accurate feedback, and the resulting feedback is often sparse and cannot effectively distinguish between trajectories that are both successful or both unsuccessful. In contrast, execution-free feedback from reward models can provide more fine-grained signals without depending on unit test cases. Despite this potential, execution-free feedback for realistic software engineering (SWE) agents remains underexplored. Aiming to develop versatile reward models that are effective across TTS and RL, however, we observe that two verifiers with nearly identical TTS performance can nevertheless yield very different results in RL. Intuitively, TTS primarily reflects the model’s ability to select the best trajectory, but this ability does not necessarily generalize to RL. To address this limitation, we identify two additional aspects that are crucial for RL training: classification accuracy and calibration. We then conduct comprehensive controlled experiments to investigate how to train a robust reward model that performs well across these metrics. In particular, we analyze the impact of various factors such as training data scale, policy mixtures, and data source composition. Guided by these investigations, we introduce SWE-RM, an accurate and robust reward model adopting a mixture-of-experts architecture with 30B total parameters and 3B activated during inference. SWE-RM substantially improves SWE agents on both TTS and RL performance. For example, it increases the accuracy of Qwen3-Coder-Flash from 51.6% to 62.0%, and Qwen3-Coder-Max from 67.0% to 74.6% on SWE-Bench Verified using TTS, achieving new state-of-the-art performance among open-source models. On RL training, SWE-RM lifts the resolve rate of execution-based counterparts by 3 absolute points on SWE-Bench Verified.

Large language models (LLMs) have significantly advanced protein representation learning. However, their capacity to interpret and design antibodies through natural language remains limited. To address this challenge, we present AFD-Instruction, the first large-scale instruction dataset with functional annotations tailored to antibodies. This dataset encompasses two key components: antibody understanding, which infers functional attributes directly from sequences, and antibody design, which enables de novo sequence generation under functional constraints. These components provide explicit sequence-function alignment and support antibody design guided by natural language instructions. Extensive instruction-tuning experiments on general-purpose LLMs demonstrate that AFD-Instruction consistently improves performance across diverse antibody-related tasks. By linking antibody sequences with textual descriptions of function, AFD-Instruction establishes a new foundation for advancing antibody modeling and accelerating therapeutic discovery.

Visual reasoning is challenging, requiring both precise object grounding and understanding complex spatial relationships. Existing methods fall into two camps: language-only chain-of-thought approaches, which demand large-scale (image, query, answer) supervision, and program-synthesis approaches which use pre-trained models and avoid training, but suffer from flawed logic and erroneous grounding. We propose an annotation-free training framework that improves both reasoning and grounding. Our framework uses AI-powered verifiers: an LLM verifier refines LLM reasoning via reinforcement learning, while a VLM verifier strengthens visual grounding through automated hard-negative mining, eliminating the need for ground truth labels. This design combines the strengths of modern AI systems: advanced language-only reasoning models for decomposing spatial queries into simpler subtasks, and strong vision specialist models improved via performant VLM critics. We evaluate our approach across diverse spatial reasoning tasks, and show that our method improves visual reasoning and surpasses open-source and proprietary models, while with our improved visual grounding model we further outperform recent text-only visual reasoning methods. Project webpage: https://glab-caltech.github.io/valor/

Despite recent advancements in extending context windows of large language models (LLMs) and large vision-language models (LVLMs), their ability to perform complex multi-modal reasoning over extended contexts remains critically limited. To underline this challenge, we present MMReD, a benchmark specifically designed to assess reasoning abilities within dense, information-rich scenarios where simple retrieval is not enough. Unlike traditional Needle-in-a-Haystack evaluations, MMReD challenges models to identify and interpret global patterns across entire contexts. Our benchmark comprises 24 tasks of varying complexity, ranging from standard passkey retrieval setups to those requiring selective or uniform attention to all context chunks. The evaluation reveals a consistent performance drop across all tested models -- including the most advanced LLMs, LVLMs, and architectures specializing in code and reasoning -- as the number of observations increases. Notably, even the leading reasoning-specialized models achieve 0\% accuracy on certain tasks at the maximum context length of 128 observations. Conventional fine-tuning techniques, such as SFT and GRPO, also fail to generalize effectively to longer contexts. These observations reveal an inherent limitation in current model architectures, emphasizing the need for innovative approaches to enable competent dense context reasoning in multi-modal AI systems.

The ``Heatmap + Monte Carlo Tree Search (MCTS)'' paradigm has recently emerged as a prominent framework for solving the Travelling Salesman Problem (TSP). While considerable effort has been devoted to enhancing heatmap sophistication through advanced learning models, this paper rigorously examines whether this emphasis is justified, critically assessing the relative impact of heatmap complexity versus MCTS configuration. Our extensive empirical analysis across diverse TSP scales, distributions, and benchmarks reveals two pivotal insights: \textbf{1}) The configuration of MCTS strategies significantly influences solution quality, underscoring the importance of meticulous tuning to achieve optimal results and enabling valid comparisons among different heatmap methodologies. \textbf{2}) A rudimentary, parameter-free heatmap based on the intrinsic $k$-nearest neighbor structure of TSP instances, when coupled with an optimally tuned MCTS, can match or surpass the performance of more sophisticated, learned heatmaps, demonstrating robust generalizability on problem scale and distribution shift. To facilitate rigorous and fair evaluations in future research, we introduce a streamlined pipeline for standardized MCTS hyperparameter tuning. Collectively, these findings challenge the prevalent assumption that heatmap complexity is the primary determinant of performance, advocating instead for a balanced integration and comprehensive evaluation of both learning and search components within this paradigm.

Reconstructing transparent objects from a set of multi-view images is a challenging task due to the complicated nature and indeterminate behavior of light propagation. Typical methods are primarily tailored to specific scenarios, such as objects following a uniform topology, exhibiting ideal transparency and surface specular reflections, or with only surface materials, which substantially constrains their practical applicability in real-world settings. In this work, we propose a differentiable rendering framework for transparent objects, dubbed \emph{DiffTrans}, which allows for efficient decomposition and reconstruction of the geometry and materials of transparent objects, thereby reconstructing transparent objects accurately in intricate scenes with diverse topology and complex texture. Specifically, we first utilize FlexiCubes with dilation and smoothness regularization as the iso-surface representation to reconstruct an initial geometry efficiently from the multi-view object silhouette. Meanwhile, we employ the environment light radiance field to recover the environment of the scene. Then we devise a recursive differentiable ray tracer to further optimize the geometry, index of refraction and absorption rate simultaneously in a unified and end-to-end manner, leading to high-quality reconstruction of transparent objects in intricate scenes. A prominent advantage of the designed ray tracer is that it can be implemented in CUDA, enabling a significantly reduced computational cost. Extensive experiments on multiple benchmarks demonstrate the superior reconstruction performance of our \emph{DiffTrans} compared with other methods, especially in intricate scenes involving transparent objects with diverse topology and complex texture. Code will be released.

Vision-Language-Action (VLA) models represent a critical milestone toward embodied intelligence in robotic manipulation. To support their training, recent research has developed high-performance simulation engines for data synthesis. However, their effectiveness is still significantly limited by the simulation-to-reality (Sim2Real) gap, as policies trained on synthetic data often fail to generalize reliably to the real world. To address this challenge, we present Sim2Real-VLA, a generalist robot control model trained exclusively on synthetic data, yet capable of transferring seamlessly to real-world manipulation tasks. Sim2Real-VLA features a dual-system architecture: a high-level planner that infers object-centered chains-of-affordances, and a low-level actor that executes and validates these plans in real time via a tokenized action space. This design filters out manipulation-irrelevant features and prioritizes motion-critical dynamics, thereby enhancing Sim2Real domain transfer. Besides, a notable advantage of Sim2Real-VLA lies in its tight integration with automated data generation for manipulation skills, eliminating the need for manual fine-tuning and enabling scalable, hands-free training. Empirical evaluations across bimanual, dexterous, and long-horizon tasks show that Sim2Real-VLA consistently outperforms previous VLA baselines under diverse real-world environments and domain shifts.

Multimodal representation learning models have demonstrated successful operation across complex tasks, and the integration of vision-language models (VLMs) has further enabled embedding models with instruction-following capabilities. However, existing embedding models lack visual-interactive capabilities to specify regions of interests from users (e.g., point, bounding box, mask), which have been explored in generative models to broaden their human-interactive applicability. Equipping embedding models with visual interactions not only would unlock new applications with localized grounding of user intent, which remains unexplored, but also enable the models to learn entity-level information within images to complement their global representations for conventional embedding tasks. In this paper, we propose a novel **V**isual-**I**nte**R**active **T**ext-Image **U**niversal **E**mbedder (**VIRTUE**) that extends the capabilities of the segmentation model and the vision-language model to the realm of representation learning. In VIRTUE, the segmentation model can process visual prompts that pinpoint specific regions within an image, thereby enabling the embedder to handle complex and ambiguous scenarios more precisely. To evaluate the visual-interaction ability of VIRTUE, we introduce a large-scale **S**egmentation-and-Scene **Ca**ption **R**etrieval (**SCaR**) benchmark comprising 1M samples that aims to retrieve the text caption by jointly considering the entity with a specific object and image scene. VIRTUE consistently achieves a state-of-the-art performance with significant improvements across 36 universal MMEB (**3.1\%–8.5\%**) and five visual-interactive SCaR (**15.2\%–20.3\%**) tasks. The code, models, and benchmarks are available at https://github.com/sony/virtue.

Recent efforts have extended the foundation model paradigm from natural language to time series, raising expectations that pre-trained time-series foundation models generalize well across downstream tasks. In this work, we focus on time-series anomaly detection, in which time-series foundation models detect anomalies based on the reconstruction or forecasting error. Specifically, we critically examine the performance of five popular families of time-series foundation models: MOMENT, Chronos, TimesFM, Time-MoE, and TSPulse. We find that for each model family using varying model sizes and context window lengths, anomaly detection performance does not significantly differ to simple one-liner baselines: moving-window variance and squared-difference. These findings suggest that the key assumptions underlying reconstruction-based and forecasting-based methodologies for time-series anomaly detection are not satisfied for time-series foundation models: anomalies are not consistently harder to reconstruct or forecast. The results suggest that current approaches for leveraging foundation models in anomaly detection are insufficient. Building upon our insights, we propose alternative directions to effectively detect anomalies using foundation models, thereby unlocking their full potential for time-series anomaly detection.

Large Language Model (LLM) agents are reshaping the game industry, by enabling more intelligent and human-preferable characters. Yet, current game benchmarks fall short of practical needs: they lack evaluations of diverse LLM capabilities across various game genres, studies of agentic modules crucial for complex gameplay, and fine-tuning datasets to adapt pre-trained LLMs into gaming agents. To fill these gaps, we present Orak, a benchmark for training and evaluating LLM agents across 12 popular video games spanning all major genres. Using a plug-and-play interface built on Model Context Protocol (MCP), Orak supports systematic and reproducible studies of agentic modules in varied game scenarios. We further release a fine-tuning dataset of expert LLM gameplay trajectories spanning multiple genres, turning general LLMs into effective game agents. Orak offers a comprehensive evaluation framework, including game leaderboards, LLM battle arenas, and in-depth analyses of input modality, agentic strategies, and fine-tuning effects, establishing a foundation towards versatile gaming agents. Code is available at https://anonymous.4open.science/r/Orak-5013/.

A central objective of manipulation policy design is to enable robots to comprehend human instructions and predict generalized actions in unstructured environments. Recent autoregressive vision-language-action (VLA) approaches discretize actions into bins to exploit the pretrained reasoning and generation paradigms of vision-language models (VLMs). While these models achieve efficient and scalable training, the discretization undermines the continuity required for precise control. In contrast, diffusion-based VLA methods incorporate an additional diffusion head to predict continuous actions, but they rely solely on feature representations extracted from the VLM, without leveraging the pretrained large language model (LLM) as an expert for iterative action generation. To integrate the complementary strengths of autoregressive and diffusion generation, we introduce HybridVLA, which innovatively leverages a shared LLM backbone to perform iterative action prediction through both paradigms. Specifically, a collaborative training recipe is proposed, incorporating diffusion denoising into the next-token prediction process and mitigating interference between the two generation paradigms. With this recipe, we find these two action prediction methods not only reinforce each other but also exhibit varying strengths across different scenarios. Therefore, we design a collaborative action ensemble mechanism that adaptively fuses both predictions, leading to more robust control. HybridVLA outperforms previous state-of-the-art VLA methods by 17\% and 19\% in mean success rate on simulation and real-world tasks, respectively, while demonstrating generalization to unseen configurations.

Subject-agnostic brain decoding, which aims to reconstruct continuous visual experiences from fMRI without subject-specific training, holds great potential for clinical applications. However, this direction remains underexplored due to challenges in cross-subject generalization and the complex nature of brain signals. In this work, we propose Visual Cortex Flow Architecture (VCFlow), a novel hierarchical decoding framework that explicitly models the ventral-dorsal architecture of the human visual system to learn multi-dimensional representations. By disentangling and leveraging features from early visual cortex, ventral, and dorsal streams, VCFlow captures diverse and complementary cognitive information essential for visual reconstruction. Furthermore, we introduce a feature-level contrastive learning strategy to enhance the extraction of subject-invariant semantic representations, thereby enhancing subject-agnostic applicability to previously unseen subjects. Unlike conventional pipelines that need more than 12 hours of per-subject data and heavy computation, VCFlow sacrifices only 7\% accuracy on average yet generates each reconstructed video in 10 seconds without any retraining, offering a fast and clinically scalable solution.

Autoregressive (AR) models are promising for image generation, yet continuous-token AR variants often trail latent diffusion and masked-generation models. The core issue is heterogeneous variance in VAE latents, which is amplified during AR decoding, especially under classifier-free guidance (CFG), and can cause variance collapse. We propose SphereAR to address this issue. Its core design is to constrain all AR inputs and outputs---including after CFG---to lie on a fixed-radius hypersphere (constant $\ell_2$ norm), leveraging hyperspherical VAEs. Our theoretical analysis shows that hyperspherical constraint removes the scale component (the primary cause of variance collapse), thereby stabilizing AR decoding. Empirically, on ImageNet generation, SphereAR-H (943M) sets a new state of the art for AR models, achieving FID 1.34. Even at smaller scales, SphereAR-L (479M) reaches FID 1.54 and SphereAR-B (208M) reaches 1.92, matching or surpassing much larger baselines such as MAR-H (943M, 1.55) and VAR-d30 (2B, 1.92). To our knowledge, this is the first time a pure next-token AR image generator with raster order surpasses diffusion and masked-generation models at comparable parameter scales.

Advances in training and architectural design have enabled LLMs with million-token context windows, yet in practice these models often read far more than they can reliably use. While inference-time compute scaling—typically via “thinking tokens”—can help on short multi-step reasoning tasks, our controlled long-context experiments show rapidly diminishing returns that collapse as context grows. We trace this to score dilution in static self-attention and prove that, in such regimes, decoding more tokens cannot reliably recover buried evidence. We propose query-only test-time training (qTTT): a cache-preserving adaptation that performs a single prefill to fix keys/values and then applies a handful of gradient updates to the query projections. qTTT provably increases the target–distractor margin and, empirically, delivers consistent gains across model sizes and benchmarks. On Qwen3-4B, qTTT improves average accuracy by +12.6 and +14.1 absolute points on LongBench-v2 and ZeroSCROLLS, respectively. The practical takeaway is simple: for long contexts, spending a small inference-time budget on context-specific adaptation is a more effective use of compute than generating additional thinking tokens.

LLMs can perform seemingly planning-intensive tasks, like writing coherent stories or functioning code, without explicitly verbalizing a plan; however, the extent to which they implicitly plan is unknown. In this paper, we define *latent planning* as occurring when LLMs possess internal planning representations that (1) cause the generation of a specific future token or concept, and (2) shape preceding context to license said future token or concept. We study the Qwen-3 family (0.6B-14B) on simple planning tasks, finding that latent planning ability increases with scale. Models that plan possess features that represent a planned-for word like *accountant*, and cause them to output *an* rather than *a*; moreover, even the less-successful Qwen-3 4B-8B have nascent planning mechanisms. On the more complex task of completing rhyming couplets, we find that models often identify a rhyme ahead of time, but even large models seldom plan far ahead. However, we can elicit some planning that increases with scale when steering models towards planned words in prose. In sum, we offer a framework for measuring planning and mechanistic evidence of how models' planning abilities grow with scale.

In the world of Harry Potter, when Dumbledore's mind is overburdened, he extracts memories into a Pensieve to be revisited later. In the world of AI, while we possess the Pensieve—mature databases and retrieval systems, our models inexplicably lack the "wand" to operate it. They remain like a Dumbledore without agency, passively accepting a manually engineered context as their entire memory. This work finally places the wand in the model's hand. We introduce StateLM, a new class of foundation models endowed with an internal reasoning loop to manipulate their own state. We equip our model with a suite of tools, such as dynamic indexing, context pruning, and note-taking, and train it to actively manage this loop. By learning to dynamically construct its own context, our model breaks free from the architectural prison of a fixed window. The results are prominent: our state-management approach decouples performance from context window size, delivering strong accuracy and sustainability under extremely long contexts with linear inference cost. We demonstrate this by showing StateLM reliably retrieves a "needle" from a 1-million-token haystack, a task far beyond the reach of conventional models. On practical document QA tasks from NovelQA and $\infty$Bench, StateLM outperforms strong instruct baselines while using only 1/4 of their active context. An ablation further shows that our curated training pipeline is more effective for learning memory management than agent-like prompting. Together, these results mark a shift from passive predictors to state-aware systems where reasoning becomes a stateful and manageable process.