ICLR 2026 Papers

Universal image restoration (UIR) aims to recover images degraded by unknown mixtures while preserving semantics—conditions under which discriminative restorers and UNet-based diffusion priors often oversmooth, hallucinate, or drift. We present LucidFlux, a caption-free UIR framework that adapts a large diffusion transformer (Flux.1) to restoration with minimal parameter overhead. LucidFlux introduces a lightweight \emph{dual-branch conditioner} that injects signals from the degraded input and a lightly restored proxy to respectively anchor geometry and suppress artifacts. A timestep- and layer-adaptive modulation schedule routes these cues across the backbone’s hierarchy, yielding coarse-to-fine, context-aware updates that protect global structure while recovering texture. To avoid the latency and instability of text prompts or VLM captions, we enforce \emph{caption-free semantic alignment} via SigLIP features extracted from the proxy. A scalable curation pipeline further filters large-scale data for structure-rich supervision. Across synthetic and in-the-wild benchmarks, LucidFlux consistently surpasses strong open-source and commercial baselines across seven metrics, with clear visual gains in realism, detail, and artifact suppression. Ablations confirm that, for large DiTs, when, where, and what to condition—rather than scaling parameters or relying on text prompts—is the key lever for robust, prompt-free restoration.

Recently, significant progress has been made in protein-ligand docking, especially in deep learning methods, and some benchmarks were proposed, such as PoseBench and PLINDER. However, these studies typically focus on the self-docking scenario, which is less practical in real-world applications. Moreover, some studies involve heavy frameworks requiring extensive training, posing challenges to convenient and efficient assessment of docking methods. To fill these gaps, we design PoseX, an open-source benchmark to evaluate both self-docking and cross-docking, enabling a practical and comprehensive assessment of algorithmic advances. Specifically, we curated a novel dataset comprising 718 entries for self-docking and 1,312 entries for cross-docking; secondly, we incorporated 23 docking methods in three methodological categories, including physics-based methods (e.g., Schrödinger Glide), AI docking methods (e.g., DiffDock) and AI co-folding methods (e.g., AlphaFold3); thirdly, we developed a relaxation method for post-processing to minimize conformational energy and refine binding poses; fourthly, we established a public leaderboard to rank submitted models in real-time. We derived some key insights and conclusions through extensive experiments: (1) AI-based approaches consistently outperform physics-based methods in overall docking success rate. (2) Most intra- and intermolecular clashes of AI-based approaches can be greatly alleviated with relaxation, which means combining AI modeling with physics-based post-processing could achieve excellent performance. (3) AI co-folding methods exhibit ligand chirality issues, except for Boltz-1x, which introduced physics-inspired potentials to fix hallucinations, suggesting that stereochemical modeling greatly improves the structural plausibility of the predicted protein-ligand complexes. (4) Specifying binding pockets significantly promotes docking performance, indicating that pocket information can be leveraged adequately, particularly for AI co-folding methods, in future modeling efforts.

Classical Federated Learning relies on a multi-round iterative process of model exchange and aggregation between server and clients, with high communication costs and privacy risks from repeated model transmissions. In contrast, one-shot federated learning (OFL) alleviates these limitations by reducing communication to a single round, thereby lowering overhead and enhancing practical deployability. Nevertheless, most existing one-shot approaches remain either impractical or constrained, for example, they often depend on the availability of a public dataset, assume homogeneous client models, or require uploading additional data or model information. To overcome these issues, we introduce the Gaussian-Head OFL (GH-OFL) family, a suite of one-shot federated methods that assume class-conditional Gaussianity of pretrained embeddings. Clients transmit only sufficient statistics (per-class counts and first/second-order moments) and the server builds heads via three components: (i) Closed-form Gaussian heads (NB/LDA/QDA) computed directly from the received statistics; (ii) FisherMix, a linear head with cosine margin trained on synthetic samples drawn in an estimated Fisher subspace; and (iii) Proto-Hyper, a lightweight low-rank residual head that refines Gaussian logits via knowledge distillation on those synthetic samples. In our experiments, GH-OFL methods deliver state-of-the-art robustness and accuracy under strong non-IID skew while remaining strictly data-free.

While deep reinforcement learning (DRL) from pixels has achieved remarkable success, its sample inefficiency remains a critical limitation for real-world applications. Model-based RL (MBRL) addresses this by learning a world model to generate simulated experience, but standard approaches that rely on pixel-level reconstruction losses often fail to capture small, task-critical objects in complex, dynamic scenes. We posit that an object-centric representation can direct model capacity toward semantically meaningful entities, improving dynamics prediction and sample efficiency. In this work, we introduce **OC-STORM**, an object-centric MBRL framework that enhances a learned world model with object representations extracted by a pretrained segmentation network. By conditioning on a minimal number of annotated frames, OC-STORM learns to track decision‐relevant object dynamics and inter‑object interactions without extensive labeling or access to privileged information. Empirical results demonstrate that OC-STORM significantly outperforms the STORM baseline on the Atari 100k benchmark and achieves state-of-the-art sample efficiency on challenging boss fights in the visually complex game **Hollow Knight**. Our findings underscore the potential of integrating object-centric priors into MBRL for complex visual domains. Core code and evaluation videos are available in supplementary materials.

Large language models remain vulnerable to jailbreak attacks, inputs crafted to bypass safety mechanisms and elicit harmful responses, despite advances in alignment and instruction tuning. Existing attacks often rely on prompt rewrites, dense optimization, or ad hoc heuristics, and lack interpretability and robustness. We propose **Head-Masked Nullspace Steering (HMNS)**, a circuit-level intervention that (i) identifies attention heads most causally responsible for a model’s default behavior, (ii) suppresses their write paths via targeted column masking, and (iii) injects a perturbation constrained to the orthogonal complement of the muted subspace. This geometry-aware intervention preserves fluency while steering the model toward completions that differ from baseline routing. HMNS operates in a closed-loop detection–intervention cycle, re-identifying causal heads and reapplying interventions across multiple decoding attempts. Across multiple jailbreak benchmarks, strong safety defenses, and widely used language models, HMNS attains state-of-the-art attack success rates with fewer queries than prior methods. Ablations confirm that nullspace-constrained injection, residual norm scaling, and iterative re-identification are key to its effectiveness. To our knowledge, this is the first jailbreak method to leverage geometry-aware, interpretability-informed interventions, highlighting a new paradigm for controlled model steering and adversarial safety circumvention.

Large Multimodal Models (LMMs) are inherently modular, consisting of vision and audio encoders, projectors, and large language models. Yet, they are almost always executed monolithically, which underutilizes the heterogeneous accelera- tors (NPUs, GPUs, DSPs) in modern SoCs and leads to high end-to-end latency. In this paper, we present NANOMIND, a hardware–software co-design inference framework for Large Multimodal Models (LMMs) that breaks large models into modular “bricks” (vision, language, audio, etc.) and maps each to its ideal accelera- tor. The key insight is that large models can be broken into modular components and scheduled to run on the most appropriate compute units. It performs module-level dynamic offloading across accelerators on unified-memory SoCs. By combining customized hardware design, system-level scheduling, and optimized low-bit com- putation kernels, we demonstrate our framework with a compact, battery-powered device capable of running LMMs entirely on-device. This prototype functions as a self-contained intelligent assistant that requires no network connectivity, while achieving higher throughput and superior power efficiency under strict resource constraints. The design further bypasses CPU bottlenecks and reduces redundant memory usage through token-aware buffer management and module-level coordi- nation. Our system outperforms existing implementations in resource efficiency, cutting energy consumption by 42.3% and GPU memory usage by 11.2%. This enables a battery-powered device to run LlaVA-OneVision-qwen2-05B with a camera for nearly 20.8 hours.

Large language model (LLM)–based agents are increasingly trained with reinforcement learning (RL) to enhance their ability to interact with external environments through tool use, particularly in search-based settings that require multi-turn reasoning and knowledge acquisition. However, existing approaches typically rely on outcome-based rewards that are only provided at the final answer. This reward sparsity becomes particularly problematic in multi-turn settings, where long trajectories exacerbate two critical issues: (i) advantage collapse, where all rollouts receive identical rewards and provide no useful learning signals, and (ii) lack of fine-grained credit assignment, where dependencies between turns are obscured, especially in long-horizon tasks. In this paper, we propose Information Gain-based Policy Optimization (IGPO), a simple yet effective RL framework that provides dense and intrinsic supervision for multi-turn agent training. IGPO models each interaction turn as an incremental process of acquiring information about the ground truth, and defines turn-level rewards as the marginal increase in the policy’s probability of producing the correct answer. These intrinsic rewards are combined with outcome-level supervision to form dense reward trajectories. Extensive experiments on both in-domain and out-of-domain benchmarks demonstrate that IGPO consistently outperforms strong baselines, achieving higher accuracy and improved sample efficiency.

Audio and music generation based on flexible multimodal control signals is a widely applicable topic, with the following key challenges: 1) a unified multimodal modeling framework, and 2) large-scale, high-quality training data. As such, we propose AudioX, a unified framework for anything-to-audio generation that integrates varied multimodal conditions (i.e., text, video, image, and audio signals) in this work. The core design in this framework is a Multimodal Adaptive Fusion module, which enables the effective fusion of diverse multimodal inputs, enhancing cross-modal alignment and improving overall generation quality. To train this unified model, we construct a large-scale, high-quality dataset, IF-caps, comprising over 7 million samples curated through a structured data annotation pipeline. This dataset provides comprehensive supervision for multimodal-conditioned audio generation. We benchmark AudioX against state-of-the-art methods across a wide range of tasks, finding that our model achieves superior performance, especially in text-to-audio and text-to-music generation. These results demonstrate our method is capable of audio generation under multimodal control signals, showing powerful instruction-following potential. We will release the code, model, and dataset.

In this paper, we explore how directly pretraining a value model simplifies and stabilizes reinforcement learning from human feedback (RLHF). In reinforcement learning, value estimation is the key to policy optimization, distinct from reward supervision. The value function predicts the \emph{return-to-go} of a partial answer, that is, how promising the partial answer is if it were continued to completion. In RLHF, however, the standard pipeline first pretrains a reward model and then learns a value function online, even though no new reward signals are available once preference data is collected. This makes critic learning redundant, as the process of training a reward model and then deriving a value model is informationally equivalent to directly pretraining a value model. Importantly, this requires no additional supervision, and our value model is trained on exactly the same data used for reward modeling. Building on this insight, we introduce \emph{Decoupled Value Policy Optimization} (DVPO), a framework that pretrains a \emph{Global Value Model} (GVM) offline and freezes it as a universal critic for policy learning. The GVM provides stable, fine-grained credit assignment without critic drift or trajectory sampling. Experiments across MT-Bench, Alpaca-Eval, and Arena-Hard demonstrate that DVPO matches or surpasses state-of-the-art RLHF methods. These results highlight RLHF can be reframed as policy-only optimization guided by a single pretrained value model. The implementation code for our method is available in \url{https://github.com/microsoft/DKI_LLM/tree/main/dvpo}

Controllable generation is a fundamental task in NLP with many applications, providing a basis for function calling to agentic communication. However, even state-of-the-art autoregressive Large Language Models (LLMs) today exhibit unreliability when required to generate structured output. Inspired by the current new diffusion-based large language models (dLLM), we realize that the architectural difference, especially the global information-sharing mechanism for language modeling, may be the key to unlock next-level controllable generation. To explore the possibility, we propose Self-adaptive Schema Scaffolding ($S^3$), a novel framework that enables dLLM to stably generate reliable structured outputs (e.g., JSON) by utilizing its innate reverse reasoning capability and global context awareness. $S^3$ initiates a schematic template directly in the output context as a starting state for dLLM, offering a more robust and general method than intricate prompt optimization. Experiments demonstrate that our method substantially unlocks the dLLM’s potential in controllable generation in terms of structure adherence, content fidelity, and faithfulness. These results establish new perspectives and practical pathways for deploying language models in controllable generation tasks.

Accurate prediction of protein-ligand binding affinities remains a cornerstone problem in drug discovery. While binding affinity is inherently dictated by the 3D structure and dynamics of protein-ligand complexes, current deep learning approaches are limited by the lack of high-quality experimental structures with annotated binding affinities. To address this limitation, we introduce the Structurally Augmented IC50 Repository (SAIR), the largest publicly available dataset of protein-ligand 3D structures with associated activity data. The dataset comprises $5,244,285$ structures across $1,048,857$ unique protein-ligand systems, curated from the ChEMBL and BindingDB databases, which were then computationally folded using the Boltz-1x model. We provide a comprehensive characterization of the dataset, including distributional statistics of proteins and ligands, and evaluate the structural fidelity of the folded complexes using PoseBusters. Our analysis reveals that approximately $3 \%$ of structures exhibit physical anomalies, predominantly related to internal energy violations. As an initial demonstration, we benchmark several binding affinity prediction methods, including empirical scoring functions (Vina, Vinardo), a 3D convolutional neural network (Onionnet-2), and a graph neural network (AEV-PLIG). While machine learning-based models consistently outperform traditional scoring function methods, neither exhibit a high correlation with ground truth affinities, highlighting the need for models specifically fine-tuned to synthetic structure distributions. This work provides a foundation for developing and evaluating next-generation structure and binding-affinity prediction models and offers insights into the structural and physical underpinnings of protein-ligand interactions. The link to the data will be added upon publication, to preserve anonymity of the submission.

We introduce TangoFlux, an efficient Text-to-Audio (TTA) generative model with 515M parameters, capable of generating up to 30 seconds of 44.1kHz audio in 3.7 seconds on a A40 GPU. A key challenge in aligning TTA models lies in creating preference pairs, as TTA lacks structured mechanisms like verifiable rewards or gold-standard answers available for Large Language Models (LLMs). To address this, we propose CLAP-Ranked Preference Optimization (CRPO), a novel framework that iteratively generates and optimizes preference data to enhance TTA alignment. We show that the audio preference dataset generated using CRPO outperforms the static alternatives. With this framework, TangoFlux achieves state-of-the-art performance across both objective and subjective benchmarks. https://tangoflux.github.io/ holds the model-generated audio samples for comparison.

Perceiving visual semantics embedded within consecutive characters is a crucial yet under-explored capability for both Large Language Models (LLMs) and Multi-modal Large Language Models (MLLMs). In this work, we select ASCII art as a representative artifact. It depicts concepts through careful arrangement of characters, which can be formulated in both text and image modalities. We frame the problem as a recognition task, and construct a novel benchmark, ASCIIEval. It covers over 3K samples with an elaborate categorization tree, along with a training set for further enhancement. Encompassing a comprehensive analysis of tens of models through different input modalities, our benchmark demonstrate its multi-faceted diagnostic power. Given textual input, language models shows their visual perception ability on ASCII art concepts. Proprietary models achieve over 70\% accuracy on certain categories, with GPT-5 topping the rank. For image inputs, we reveal that open-source MLLMs suffer from a trade-off between fine-grained text recognition and collective visual perception. They exhibit limited generalization ability to this special kind of arts, leading to the dramatic gap of over 20.01\% accuracy compared with their proprietary counterparts. Another critical finding is that model performance is sensitive to the length of the ASCII art, with this sensitivity varying across input modalities. Unfortunately, none of the models could successfully benefit from the simultaneous provision of both modalities, highlighting the need for more flexible modality-fusion approaches. Besides, we also introduce approaches for further enhancement and discuss future directions. Resources are available at https://anonymous.4open.science/r/VisionInText-9EE5.

We study the statistical performance of a continual learning problem with two linear regression tasks in a well-specified random design setting. We consider a structural regularization algorithm that incorporates a generalized $\ell_2$-regularization tailored to the Hessian of the previous task for mitigating catastrophic forgetting. We establish upper and lower bounds on the joint excess risk for this algorithm. Our analysis reveals a fundamental trade-off between memory complexity and statistical efficiency, where memory complexity is measured by the number of vectors needed to define the structural regularization. Specifically, increasing the number of vectors in structural regularization leads to a worse memory complexity but an improved excess risk, and vice versa. Furthermore, our theory suggests that naive continual learning without regularization suffers from catastrophic forgetting, while structural regularization mitigates this issue. Notably, structural regularization achieves comparable performance to joint training with access to both tasks simultaneously. These results highlight the critical role of curvature-aware regularization for continual learning.

Playing video games requires perception, reasoning, memory, and long-horizon planning—exactly the faculties expected of modern large language and vision–language models (LLMs/VLMs). We introduce LMGame-Bench, a benchmark built on six popular games spanning platformer, puzzle, and narrative games through a unified Gym‑style API. Unlike prior game benchmarks that entangle multiple skills, LMGame-Bench employs a modular harness—including perception, memory, and reasoning modules—that can be toggled to selectively probe distinct capabilities. The benchmark further improves robustness through prompt standardization and contamination mitigation. Evaluation of 13 state-of-the-art models demonstrates that LMGame-Bench remains challenging yet effectively discriminates among models. Correlation analysis reveals that individual games align with core LLM capabilities, providing a quantitative framework for interpreting performance. Finally, LMGame-Bench exposes models’ limitations in visual state extraction, reflection, spatiotemporal reasoning, and long-context reasoning, pointing to concrete directions for model improvement.

Irregular temporal data, characterized by varying recording frequencies, differing observation durations, and missing values, presents significant challenges across fields like mobility, healthcare, and environmental science. Existing research communities often overlook or address these challenges in isolation, leading to fragmented tools and methods. To bridge this gap, we introduce a unified framework, and the first standardized dataset repository for irregular time series classification, built on a common array format to enhance interoperability. This repository comprises 34 datasets on which we benchmark 12 classifier models from diverse domains and communities. This work aims to centralize research efforts and enable a more robust evaluation of irregular temporal data analysis methods.

Policy gradient algorithms have been successfully applied to enhance the reasoning capabilities of large language models (LLMs). KL regularization is ubiquitous, yet the design surface, choice of KL direction (forward vs. reverse), normalization (normalized vs. unnormalized), and estimator ($k_1/k_2/k_3$), is scattered across the literature and often intertwined with off-policy estimation. We ask a focused question: under the off-policy setting, what weighting is required for each KL variant so that the surrogate we optimize yields the exact gradient of the intended KL-regularized objective? We answer this with a compact, unified derivation we call the Regularized Policy Gradient (\textbf{RPG}) view. RPG (i) unifies normalized and unnormalized KL variants and shows that the widely-used $k_3$ penalty is exactly the unnormalized KL; (ii) specifies conditions under which REINFORCE-style losses with stop-gradient are gradient-equivalent to fully differentiable surrogates; (iii) identifies and corrects an off-policy importance-weighting mismatch in GRPO's KL term; and (iv) introduces RPG-Style Clip, a truncated-importance-sampling step within RPG-REINFORCE that enables stable, off-policy policy-gradient training at scale. On mathematical reasoning benchmarks (AIME24, AIME25), RPG-REINFORCE with RPG-Style Clip improves accuracy by up to $+6$ absolute percentage points over DAPO. Notably, RPG is a \emph{stable and scalable} RL algorithm for LLM reasoning, realized via (a) a KL-correct objective, (b) truncated importance sampling, and (c) an iterative reference-policy update scheme.

Interventional causal discovery seeks to identify causal relations by leveraging distributional changes introduced by interventions, even in the presence of latent confounders. Beyond the spurious dependencies induced by latent confounders, we highlight a common yet often overlooked challenge in the problem due to post-treatment selection, in which samples are selectively included in datasets after interventions. This fundamental challenge widely exists in biological studies; for example, in gene expression analysis, both observational and interventional samples are retained only if they meet quality control criteria (e.g., highly active cells). Neglecting post-treatment selection may introduce spurious dependencies and distributional changes under interventions, which can mimic causal responses, thereby distorting causal discovery results and challenging existing causal formulations. To address this, we introduce a novel causal formulation that explicitly models post-treatment selection and reveals how its differential reactions to interventions can distinguish causal relations from selection patterns, allowing us to go beyond traditional equivalence classes toward the underlying true causal structure. We then characterize its Markov properties and propose a $\mathcal{F}$ine-grained $\mathcal{I}$nterventional equivalence class, named $\mathcal{FI}$-Markov equivalence, represented by a new graphical diagram, $\mathcal{F}$-PAG. Finally, we develop a provably sound and complete algorithm, $\mathcal{F}$-FCI, to identify causal relations, latent confounders, and post-treatment selection up to $\mathcal{FI}$-Markov equivalence, using both observational and interventional data. Experimental results on synthetic and real-world datasets demonstrate that our method recovers causal relations despite the presence of both selection and latent confounders.

We examine a multi-armed bandit problem with contextual information, where the objective is to ensure that each arm receives a minimum aggregated reward across contexts while simultaneously maximizing the total cumulative reward. This framework captures a broad class of real-world applications where fair revenue allocation is critical and contextual variation is inherent. The cross-context aggregation of minimum reward constraints, while enabling better performance and easier feasibility, introduces significant technical challenges—particularly the absence of closed-form optimal allocations typically available in standard MAB settings. We design and analyze algorithms that either optimistically prioritize performance or pessimistically enforce constraint satisfaction. For each algorithm, we derive problem-dependent upper bounds on both regret and constraint violations. Furthermore, we establish a lower bound demonstrating that the dependence on the time horizon in our results is optimal in general and revealing fundamental limitations of the free exploration principle leveraged in prior work.