ICLR 2026 论文列表

Virtual screening (VS) aims to identify bioactive compounds from vast chemical libraries, but remains difficult in low-label regimes where only a few actives are known. Existing methods largely rely on general-purpose molecular fingerprints and overlook class-discriminative substructures critical to bioactivity. Moreover, they consider molecules independently, limiting effectiveness in low-label regimes. We introduce SubDyve, a network-based VS framework that constructs a subgraph-aware similarity network and propagates activity signals from a small known actives. When few active compounds are available, SubDyve performs iterative seed refinement, incrementally promoting new candidates based on local false discovery rate. This strategy expands the seed set with promising candidates while controlling false positives from topological bias and overexpansion. We evaluate SubDyve on ten DUD-E targets under zero-shot conditions and on the CDK7 target with a 10-million-compound ZINC dataset. SubDyve consistently outperforms existing fingerprint or embedding-based approaches, achieving margins of up to +34.0 on the BEDROC and +24.6 on the $EF_{1\\%}$ metric.

Classifier-free Guidance (CFG) is a widely used technique in modern diffusion models for generating high-quality samples. However, through an empirical analysis on both Gaussian mixture models with closed-form solutions and real-world data distributions, we observe a discrepancy between the suboptimal results produced by CFG and the ground truth. The model's excessive reliance on these suboptimal predictions often leads to low fidelity and semantic incoherence. To address this issue, we first empirically demonstrate that the model's suboptimal predictions can be effectively refined using sub-networks of the model itself, without requiring additional training or the integration of external modules. Building on this insight, we propose **$S^2$-Guidance ($S$tochastic $S$elf-Guidance)**, a novel method that leverages stochastic block-dropping during the denoising process to construct sub-networks. This approach effectively guides the model away from potential low-quality predictions, thereby improving sample quality. Extensive qualitative and quantitative experiments across multiple standard benchmarks for text-to-image and text-to-video generation tasks demonstrate that **$S^2$-Guidance** delivers superior performance, consistently surpassing CFG and other advanced guidance strategies. Our code will be released.

Proper Orthogonal Decomposition (POD) is a cornerstone reduced-order modeling technique for accelerating the solution of partial differential equations (PDEs) by extracting energy-optimal orthogonal bases. However, POD's inherent linear assumption limits its expressive power for complex nonlinear dynamics, and its snapshot-based fixed bases generalize poorly to unseen scenarios. Meanwhile, emerging deep learning solvers have explored integrating decomposition architectures, yet their purely data-driven nature lacks essential physical priors and leads to modal collapse, where decomposed modes lose discriminative power. To address these challenges, we revisit POD from an information-theoretic perspective. We theoretically establish that POD's classical energy-maximization criterion is, in essence, a principle of maximizing mutual information. Guided by this insight, we propose OrthoSolver, a neural POD framework that generalizes this core information-theoretic principle to the nonlinear domain. OrthoSolver iteratively and adaptively extracts a set of compact and expressive nonlinear basis modes by directly maximizing their mutual information with the data field. Furthermore, an orthogonality regularization is imposed to preserve the diversity of the learned modes and effectively mitigate mode collapse. Extensive experiments on seven PDE benchmarks demonstrate that OrthoSolver consistently outperforms state-of-the-art deep learning baselines.

Large language models (LLMs) have achieved remarkable progress in code generation, yet their potential for software protection remains largely untapped. Reverse engineering continues to threaten software security, while traditional virtual machine protection (VMP) relies on rigid, rule-based transformations that are costly to design and vulnerable to automated analysis. In this work, we present the first protection-aware framework that learns robust representations of VMP-protected code. Our approach builds large-scale paired datasets of source code and normalized VM implementations, and introduces hierarchical dependency modeling at intra-, preceding-, and inter-instruction levels. We jointly optimize language modeling with functionality-aware and protection-aware contrastive objectives to capture both semantic equivalence and protection strength. To further assess resilience, we propose a protection effectiveness optimization task that quantifies and ranks different VM variants derived from the same source. Coupled with a two-stage continual pre-training and fine-tuning pipeline, our method enables models to generate, compare, and reason over protected code. Extensive experiments show that our framework significantly improves robustness across diverse protection levels, opening a new research direction for learning-based software defense. In this work, we present ShieldedCode, the first protection-aware framework that learns robust representations of VMP-protected code. Our method achieves 26.95% Pass@1 on L0 VM code generation compared to 22.58% for GPT-4o., and improves binary similarity detection Recall@1 by 10\% over state of art methods like jTrans.

Quantization techniques are essential for the deployment of Large Language Models (LLMs) on edge devices. However, prevailing methods often rely on mixed-precision multiplication that lacks efficient hardware support, making it not feasible. Ternary weight quantization addresses this by constraining weights to {-1, 0, 1}, replacing expensive multiplications with hardware-efficient additions. However, such aggressive compression leads to significant accuracy degradation, even after costly quantization-aware training with massive data. We identify the core issue as _**deadzone trapping**: a large number of weights are trapped at the deadzone boundary._ This occurs because these weights receive only noisy, less informative gradients, preventing stable escape from the deadzone and severely impeding model capacity and optimization. To address this issue, we propose **Tequila**, a trapping-free quantization optimization method that reactivates deadzone-trapped weights by repurposing them as dynamic biases. This allows the repurposed weights to provide a continuous signal in the forward pass and, critically, receive direct, meaningful gradient signals during backpropagation, thereby enhancing model capacity and optimization with nearly _zero_ inference overhead. Extensive evaluations demonstrate that Tequila outperforms state-of-the-art (SOTA) ternary quantization methods across five benchmarks. Specifically, on the ARC benchmark, it achieves $>4$% accuracy gain over the SOTA baseline, nearly matching full-precision performance (within $<1$% gap) with an $3.0\times$ inference speedup. Consequently, Tequila offers a highly practical and efficient implementation for the deployment of advanced LLMs in resource-constrained environments. The code is available at \url{https://anonymous.4open.science/r/Tequila-2B5F/}

Graph neural networks (GNNs) largely rely on the message-passing paradigm, where nodes iteratively aggregate information from their neighbors. Yet, standard message passing neural networks (MPNNs) face well-documented theoretical and practical limitations. Graph positional encoding (PE) has emerged as a promising direction to address these limitations. The Euler Characteristic Transform (ECT) is an efficiently computable geometric–topological invariant that characterizes shapes and graphs. In this work, we combine the differentiable approximation of the ECT (DECT) and its local variant ($\ell$-ECT) to propose LEAP, a new end-to-end trainable local structural PE for graphs. We evaluate our approach on multiple real-world datasets as well as on a synthetic task designed to test its ability to extract topological features. Our results underline the potential of LEAP-based encodings as a powerful component for graph representation learning pipelines.

We present a scalable framework for learning deterministic and probabilistic neural surrogates for high-resolution 3D physics simulations. We introduce P3D, a hybrid CNN-Transformer backbone architecture targeted for 3D physics simulations, which significantly outperforms existing architectures in terms of speed and accuracy. Our proposed network can be pretrained on small patches of the simulation domain, which can be fused to obtain a global solution, optionally guided via a scalable sequence-to-sequence model to include long-range dependencies. This setup allows for training large-scale models with reduced memory and compute requirements for high-resolution datasets. We evaluate our backbone architecture against a large set of baseline methods with the objective to simultaneously learn 14 different types of PDE dynamics in 3D. We demonstrate how to scale our model to high-resolution isotropic turbulence with spatial resolutions of up to $512^3$. Finally, we show the versatility of our architecture by training it as a diffusion model to produce probabilistic samples of highly turbulent 3D channel flows across varying Reynolds numbers, accurately capturing the underlying flow statistics.

The Mixture-of-Experts (MoE) architecture has become a predominant paradigm for scaling large language models (LLMs). Despite offering strong performance and computational efficiency, large MoE-based LLMs like DeepSeek-V3-0324 and Kimi-K2-Instruct present serious challenges due to substantial memory requirements in deployment. While recent works have explored MoE compression to address this issue, existing methods often suffer from considerable accuracy drops (e.g., 7-14% relatively) even at modest compression rates. This paper introduces a novel Mixture-of-Basis-Experts (MoBE) method that achieves model compression while incurring minimal accuracy drops. Specifically, each up/gate matrix in an expert is decomposed via a rank decomposition as W = AB, where matrix A is unique to each expert. The relatively larger matrix B is further reparameterized as a linear combination of basis matrices {Bi} shared across all experts within a given MoE layer. The factorization is learned by minimizing the reconstruction error relative to the original weight matrices. Experiments demonstrate that MoBE achieves notably lower accuracy drops compared to prior works. For instance, MoBE can reduce the parameter counts of Qwen3-235BA22B-2507, DeepSeek-V3-0324 (671B) and Kimi-K2-Instruct (1T) by 24%-30% with only 1%-2% accuracy drop (about 2% drops when measured relatively).

Mixture-of-Experts (MoE) enables efficient scaling of large language models by activating only a subset of experts per input token. However, deploying MoE-based models incurs significant memory overhead due to the need to retain all experts in memory. While structured pruning is promising to reduce memory costs, existing methods often show suboptimal performance and unstable degradation in three dimensions: model architectures, calibration data sources, and calibration sample sizes. This paper proposes \textbf{M}ixture-\textbf{o}f-\textbf{N}ovices-and-\textbf{E}xperts (\textbf{MoNE}), a novel expert pruning method that replaces redundant experts with lightweight novices to achieve effective and robust model compression. MoNE evaluates expert redundancy based on two metrics: access frequency and output variance. Experts exhibiting low usage and stable outputs are pruned and replaced with lightweight novices—unbiased estimations of their original outputs—minimizing performance degradation. Extensive experiments demonstrate that MoNE consistently outperforms baseline methods with minimal accuracy degradation across the three dimensions, confirming its effectiveness and robustness. Notably, it outperforms baselines by up to 2.72 for the average zero shot accuracy across nine downstream tasks under 25\% pruning ratio, with only 0.14 performance drop for Qwen2-57B-A14B. The code is available at \url{https://github.com/zxgx/mode-pd}.

Achieving generalized in-hand object rotation remains a significant challenge in robotics, largely due to the difficulty of transferring policies from simulation to the real world. The complex, contact-rich dynamics of dexterous manipulation create a "reality gap" that has limited prior work to constrained scenarios involving simple geometries, limited object sizes and aspect ratios, constrained wrist poses, or customized hands. We address this sim-to-real challenge with a novel framework that enables a single policy, trained in simulation, to generalize to a wide variety of objects and conditions in the real world. The core of our method is a joint-wise dynamics model that learns to bridge the reality gap by effectively fitting limited amount of real-world collected data and then adapting the sim policy’s actions accordingly. The model is highly data‑efficient and generalizable across different whole‑hand interaction distributions by factorizing dynamics across joints, compressing system-wide influences into low‑dimensional variables, and learning each joint’s evolution from its own dynamic profile, implicitly capturing these net effects. We pair this with a fully autonomous data collection strategy that gathers diverse, real-world interaction data with minimal human intervention. Our complete pipeline demonstrates unprecedented generality: a single policy successfully rotates challenging objects with complex shapes (*e.g.*, animals), high aspect ratios (up to 5.33), and small sizes, all while handling diverse wrist orientations and rotation axes. Comprehensive real-world evaluations and a teleoperation application for complex tasks validate the effectiveness and robustness of our approach. Website: [DexNDM](https://meowuu7.github.io/DexNDM/).

Reasoning models have made rapid progress on many benchmarks involving math, code, and science. Yet, there are still many open questions about the best train- ing recipes for reasoning since state-of-the-art models often rely on proprietary datasets with little to no public information available. To address this, the goal of the OpenThoughts project is to create open-source datasets for training reasoning models. Our OpenThoughts2-1M dataset led to OpenThinker2-32B, the first model trained on public reasoning data to match DeepSeek-R1-Distill-32B on standard reasoning benchmarks such as AIME and LiveCodeBench. We then improve our dataset further by systematically investigating each step of our data genera- tion pipeline with 1,000+ controlled experiments, which led to OpenThoughts3. Scaling the pipeline to 1.2M examples and using QwQ-32B as teacher yields our OpenThinker3-7B model, which achieves state-of-the-art results: 53% on AIME 2025, 51% on LiveCodeBench 06/24-01/25, and 54% on GPQA Dia- mond – improvements of 15.3, 17.2, and 20.5 percentage points compared to the DeepSeek-R1-Distill-Qwen-7B. All of our datasets and models are available on ANONYMIZED.

Offline reinforcement learning enables policy learning solely from fixed datasets, without costly or risky environment interactions, making it highly valuable for real-world applications. While Transformer-based approaches have recently demonstrated strong sequence modeling capabilities, they typically learn from complete trajectories conditioned on final returns. To mitigate this limitation, we propose the Peak-Return Greedy Slicing (PRGS) framework, which explicitly partitions trajectories at the timestep level and emphasizes high-quality subtrajectories. PRGS first leverages an MMD-based return estimator to characterize the distribution of future returns for state-action pairs, yielding optimistic return estimates. It then performs greedy slicing to extract high-quality subtrajectories for training. During evaluation, an adaptive history truncation mechanism is introduced to align the inference process with the training procedure. Extensive experiments across multiple benchmark datasets indicate that PRGS significantly improves the performance of Transformer-based offline reinforcement learning methods by effectively enhancing their ability to exploit and recombine valuable subtrajectories.

Vision Language Models (VLMs) show strong potential for visual planning but struggle with precise spatial and long-horizon reasoning. In contrast, Planning Domain Definition Language (PDDL) planners excel at long-horizon formal planning, but cannot interpret visual inputs. Recent works combine these complementary advantages by enabling VLMs to turn visual planning problems into PDDL files for formal planning. However, while VLMs can generate PDDL problem files satisfactorily, they struggle to accurately generate the PDDL domain files, which describe all the planning rules. As a result, prior methods rely on human experts to predefine domain files or on constant environment access for refinement. We propose VLMFP, a Dual-VLM-guided framework that can autonomously generate both PDDL problem and domain files for formal visual planning. VLMFP introduces two VLMs to ensure reliable PDDL file generation: A SimVLM that simulates action consequences based on input rule descriptions, and a GenVLM that generates and iteratively refines PDDL files by comparing the PDDL and SimVLM execution results. VLMFP unleashes multiple levels of generalizability: The same generated PDDL domain file works for all the different instances under the same problem, and VLMs generalize to different problems with varied appearances and rules. We evaluate VLMFP with 6 grid-world domains and test its generalization to unseen instances, appearance, and game rules. On average, SimVLM accurately describes 95.5\%, 82.6\% of scenarios, simulates 85.5\%, 87.8\% of action sequence, and judges 82.4\%, 85.6\% goal reaching for seen and unseen appearances, respectively. With the guidance of SimVLM, VLMFP can generate PDDL files to reach 70.0\%, 54.1\% valid plans for unseen instances in seen and unseen appearances, respectively.

We introduce GradPCA, an Out-of-Distribution (OOD) detection method that exploits the low-rank structure of neural network gradients induced by Neural Tangent Kernel (NTK) alignment. GradPCA applies Principal Component Analysis (PCA) to gradient class-means, achieving more consistent performance than existing methods across standard image classification benchmarks. We provide a theoretical perspective on spectral OOD detection in neural networks to support GradPCA, highlighting feature-space properties that enable effective detection and naturally emerge from NTK alignment. Our analysis further reveals that feature quality—particularly the use of pretrained versus non-pretrained representations—plays a crucial role in determining which detectors will succeed. Extensive experiments validate the strong performance of GradPCA, and our theoretical framework offers guidance for designing more principled spectral OOD detectors.

Recent flow matching models for text-to-image generation have achieved remarkable quality, yet their integration with reinforcement learning for human preference alignment remains suboptimal, hindering fine-grained reward-based optimization. We observe that the key impediment to effective GRPO training of flow models is the temporal uniformity assumption in existing approaches: sparse terminal rewards with uniform credit assignment fail to capture the varying criticality of decisions across generation timesteps, resulting in inefficient exploration and suboptimal convergence. To remedy this shortcoming, we introduce TempFlow-GRPO (Temporal Flow-GRPO), a principled GRPO framework that captures and exploits the temporal structure inherent in flow-based generation. TempFlow-GRPO introduces three key innovations: (i) a trajectory branching mechanism that provides process rewards by concentrating stochasticity at designated branching points, enabling precise credit assignment without requiring specialized intermediate reward models; (ii) a noise-aware weighting scheme that modulates policy optimization according to the intrinsic exploration potential of each timestep, prioritizing learning during high-impact early stages while ensuring stable refinement in later phases; and (iii) a seed group strategy that controls for initialization effects to isolate exploration contributions. These innovations endow the model with temporally-aware optimization that respects the underlying generative dynamics, leading to state-of-the-art performance in human preference alignment and text-to-image benchmarks.

Whereas most brain–computer interface research has focused on decoding neural signals into behavior or intent, the reverse challenge—using controlled stimuli to steer brain activity—remains far less understood, particularly in the visual domain. However, designing images that consistently elicit desired neural responses is difficult: subjective states lack clear quantitative measures, and EEG feedback is both noisy and non-differentiable. We introduce MindPilot, the first closed-loop framework that uses EEG signals as optimization feedback to guide naturalistic image generation. Unlike prior work limited to invasive settings or low-level flicker stimuli, MindPilot leverages non-invasive EEG with natural images, treating the brain as a black-box function and employing a pseudo-model guidance mechanism to iteratively refine images without requiring explicit rewards or gradients. We validate MindPilot in both simulation and human experiments, demonstrating (i) efficient retrieval of semantic targets, (ii) closed-loop optimization of EEG features, and (iii) human-subject validations in mental matching and emotion regulation tasks. Our results establish the feasibility of EEG-guided image synthesis and open new avenues for non-invasive closed-loop brain modulation, bidirectional brain–computer interfaces, and neural signal–guided generative modeling.

Continual learning (CL) seeks models that acquire new skills without erasing prior knowledge. In exemplar-free class-incremental learning (EFCIL), this challenge is amplified because past data cannot be stored, making representation drift for old classes particularly harmful. Prototype-based EFCIL is attractive for its efficiency, yet prototypes drift as the embedding space evolves; thus, projection-based drift compensation has become a popular remedy. We show, however, that existing one-directional projections introduce systematic bias: they either retroactively distort the current feature geometry or align past classes only locally, leaving cycle inconsistencies that accumulate across tasks. We introduce bidirectional projector alignment during training: two maps, old$\to$new and new$\to$old, are trained during each new task with stop-gradient gating and a cycle-consistency objective so that transport and representation co-evolve. Analytically, we prove that the cycle loss contracts the singular spectrum toward unity in whitened space and that improved transport of class means/covariances yields smaller perturbations of classification log-odds, preserving old-class decisions and directly mitigating catastrophic forgetting. Empirically, across standard EFCIL benchmarks, our method achieves unprecedented reductions in forgetting while maintaining very high accuracy on new tasks, consistently outperforming state-of-the-art approaches.

We study the convergence rate of learning pairwise interactions in single-layer attention-style models, where tokens interact through a weight matrix and a non-linear activation function. We prove that the minimax rate is $M^{-\frac{2\beta}{2\beta+1}}$ with $M$ being the sample size, depending only on the smoothness $\beta$ of the activation, and crucially independent of token count, ambient dimension, or rank of the weight matrix. These results highlight a fundamental dimension-free statistical efficiency of attention-style nonlocal models, even when the weight matrix and activation are not separately identifiable and provide a theoretical understanding of the attention mechanism and its training.

Scalable and realistic simulation of multi-agent traffic behavior is critical for advancing autonomous driving technologies. Although existing data-driven simulators have made significant strides in this domain, they predominantly rely on supervised learning to align simulated distributions with real-world driving scenarios. A persistent challenge, however, lies in the distributional shift that arises between training and testing, which often undermines model generalization in unseen environments. To address this limitation, we propose SMART-R1, a novel R1-style reinforcement fine-tuning paradigm tailored for next-token prediction models to better align agent behavior with human preferences and evaluation metrics. Our approach introduces a metric-oriented policy optimization algorithm to improve distribution alignment and an iterative "SFT-RFT-SFT" training strategy that alternates between Supervised Fine-Tuning (SFT) and Reinforcement Fine-Tuning (RFT) to maximize performance gains. Extensive experiments on the large-scale Waymo Open Motion Dataset (WOMD) validate the effectiveness of this simple yet powerful R1-style training framework in enhancing foundation models. The results on the Waymo Open Sim Agents Challenge (WOSAC) showcase that SMART-R1 achieves state-of-the-art performance with an overall realism meta score of 0.7858, ranking first on the leaderboard at the time of submission.