中山大學HCP實驗室15篇論文被ICML 2026接收

ICML（International Conference on Machine Learning，國際機器學習會議）是機器學習與人工智能領域歷史最悠久、規模最大、影響最廣的頂級學術會議之一，也是中國計算機學會（CCF）推薦的A類會議。ICML 2026將于7月6日至11日在韓國首爾舉辦。本次大會共收到23918篇有效投稿，最終錄用6352篇，錄用率為26.6%。中山大學HCP實驗室共有15篇論文被該會議錄用，其中1篇為Spotlight論文。

Failure-Driven Workflow Refinement     (Spotlight)

Jusheng Zhang, Jing Yang, Kaitong Cai, Ziliang Chen, Yongsen Zheng, Kwok-Yan Lam, Liang Lin, Keze Wang

Workflow optimization for tool-using LLM agents is often cast as global search over candidate graphs, scored by a scalar metric. This collapses rich, multi-step failure traces into binary outcomes, obscuring recurring failure structure and making refinement inefficient. We reframe optimization as distributional refinement: each workflow induces a density over a Failure Signature Space, and the goal is to minimize its Expected Failure Mass. We propose CE-Graph, which maintains a counterexample pool, estimates dense failure modes, and applies operator-constrained graph edits via a Propose-and-Verify loop with a convergence-aware stopping rule. Across math, code, and QA benchmarks, CE-Graph improves robustness while reducing optimization cost compared to strong workflow-search baselines, suggesting reliability emerges from learning and reshaping failure landscapes rather than merely maximizing aggregate success rates.

PhyScene3D: Physically Consistent 3D Interactive Tabletop Scene Generation

Weixing Chen, Zhuoqian Feng, Yexin Zhang, Yifan Wen, Yang Liu, Yinghong Liao, Weichao Qiu, Guanbin Li, Liang Lin

Generating physically consistent 3D tabletop scenes is a fundamental yet underexplored problem for interactive and generalist robotic learning. The challenge stems from dense object hierarchies and irregular affordances. Existing methods, ranging from decoupled symbolic solvers to end-to-end regression models, often suffer from error propagation or overfitting to noisy supervision containing widespread physical violations. To address these limitations, we introduce PhyScene3D, a framework that reformulates generation as a Human-Mimetic Constructive Process. The proposed Cognitive Topological Reasoning Chain (CTRC) factorizes scene synthesis into a sequential, anchor-conditioned process under the novel 3D Axis-Aligned Bounding Box (3D AABB)-based placement scheme, thereby imposing a strong structural inductive bias. To address imperfect supervision and physical infeasibility, we introduce Physics-Aware Denoising Alignment (PADA), which integrates a differentiable Signed Distance Field (SDF) with Test-Time Optimization (TTO) to project generated scenes onto a physics-feasible manifold while preserving semantic intent. Experiments demonstrate that PhyScene3D outperforms state-of-the-art approaches in both semantic accuracy and physical validity, achieving a 40% reduction in collision rate relative to the human-annotated training data.

DDP-WM: Disentangled Dynamics Prediction for Efficient World Models

Shicheng Yin, Kaixuan Yin, Weixing Chen, Yang Liu, Guanbin Li, Liang Lin

World models are essential for autonomous robotic planning. However, the substantial computational overhead of existing dense Transformer-based models significantly hinders real-time deployment. To address this efficiency-performance bottleneck, we introduce DDP-WM, a novel world model centered on the principle of Disentangled Dynamics Prediction (DDP). We hypothesize that latent state evolution in observed scenes is heterogeneous and can be decomposed into sparse primary dynamics driven by physical interactions and secondary context-driven background updates. DDP-WM realizes this decomposition through an architecture that integrates efficient historical processing with dynamic localization to isolate primary dynamics. By employing a cross-attention mechanism for background updates, the framework optimizes resource allocation and provides a smooth optimization landscape for planners. Extensive experiments demonstrate that DDP-WM achieves superior efficiency and performance across diverse tasks, including navigation, precise tabletop manipulation, and complex deformable or multi-body interactions. Specifically, on the challenging Push-T task, DDP-WM achieves an approximately 9 times inference speedup and improves the MPC success rate from 90% to 98% compared to state-of-the-art dense models.

SOLAR for Offline MARL: Plateau-Triggered Potential Shaping under World-Model Uncertainty

Jusheng Zhang, Yijia Fan, Ruiqi Chen, Jing Yang, Ziliang Chen, Yongsen Zheng, Yanxi Chen, Jian Wang, Kwok-Yan Lam, Liang Lin, Keze Wang

Reward shaping can accelerate reinforcement learning, but in sparse-reward offline multi-agent RL it is often brittle: dense intrinsic rewards may alter the underlying Markov game, while world-model guidance can amplify model bias. We find that shaping becomes reliable when it is (i) activated only after statistically validated learning plateaus and (ii) constrained to potential-based shaping, which preserves the task optimum. Motivated by this, we propose SOLAR, a simulate--evaluate--shape framework. A learned world model enables low-cost rollouts to test plateaus; once a plateau is detected, we inject shaping in the form  with adaptively updated potentials; and we attenuate shaping using uncertainty-aware throttling in unreliable regions. We provide theoretical analysis on policy invariance and on the deviation of plateau decisions under model error, and establish stability for the resulting two-timescale adaptation. Experiments on sparse-reward offline MARL benchmarks show consistent gains in stability and final performance across dataset qualities.

NBCG: Nash-Bargained Causal Game for Long-Tailed Multi-Label NLP

Jing Yang, Jusheng Zhang, Keze Wang

Long-tailed multi-label text classification is often treated as a data scarcity problem, addressed by re-sampling or fixed re-weighting. We argue that a central failure mode is dominant coalition capture: frequent labels, amplified by spurious co-occurrences, form dominant coalitions that dominate shared representations and gradient allocation during optimization. As a result, rare labels are learned via superficial shortcuts, yielding brittle generalization under distribution shifts. We propose NBCG, a Nash-Bargained Causal Game that reformulates multi-label learning as a cooperative bargaining process among label coalitions. NBCG first leverages Neural Structural Equation Models to learn a directed dependency structure, inducing causally coherent coalitions---rather than random partitions---and coalition-specific communication masks. We then optimize a Nash bargaining objective over coalition utilities relative to an adaptive disagreement point, which serves as a principled credit-allocation mechanism: it adaptively prioritizes under-served coalitions while maintaining a Pareto-efficient trade-off among all players.

Self-Prophetic Decoding to Unlock Visual Search in LVLMs

Zhendong He, Qiyuan Dai, Guanbin Li, Liang Lin, Sibei Yang

Large Vision-Language Models (LVLMs) are rapidly evolving toward true multimodal reasoning, with visual search representing a concrete instantiation of the thinking-with-images paradigm. However, LVLM visual search faces two key challenges: incompatibility among intrinsic capabilities after post-training, and interference in long multi-step reasoning contexts. To address these, we identify two novel insights. First, self-regulation between pre- and post-training LVLMs leverages the intrinsic single-step capabilities of the pre-training model to mitigate capability deterioration and long-context interference. Second, probability-based prophetic sampling, replacing naive prompting, provides a probabilistic interface where the pre-training model acts as a prophet and the post-training model selectively accepts prophetic tokens under its output distribution, preserving coherent multi-step reasoning. Building on these insights, we introduce SeProD, a self-prophetic decoding framework that leverages intrinsic single-step capabilities to enable coherent multi-step reasoning in a training-free, plug-and-play manner. Experiments show that SeProD consistently improves multiple visual-search LVLMs across all 12 splits of 4 visual search benchmarks, as well as across general VQA benchmarks, without added computational overhead, thanks to its parallel prophetic acceptance mechanism. The code will be made publicly available.

Where Detectors Fail: Probing Generative Space for Generalizable AI-Generated Image Detection

Zijie Cao, Weijie Tu, Yao Xiao, Weijian Deng, Weiyan Chen, Liang Lin, Pengxu Wei

Detecting AI-generated images (AIGI) remains challenging because detectors often fail to generalize to unseen generators. Although existing methods are trained on large datasets, their performance still degrades when generation settings change, indicating that data scale alone is insufficient and that limited coverage of generative variations during training is a key factor. Studies on generative model editing show that small changes in internal representations can produce diverse and meaningful image variations, many of which are not explored under standard sampling. Leveraging this insight, we propose PROBE (Probing Robustness via Boundary Exploration), a framework that improves detector generalization by actively exploring challenging regions of the generative process. Instead of treating the generator as a fixed data source, PROBE uses the detector as a critic to steer the generator through manifold-level modifications, producing realistic samples that are difficult to classify. These samples expose failure cases that are uncommon under standard data sampling strategies and are used to refine the detector. Experimental results across multiple benchmarks indicate that PROBE enhances generalization to unseen generators, resulting in more generalizable AIGI detection performance.

Great Minds Think Alike: Contextual Tacit Communication for Decentralized LLM-Agent Cooperation

Yue Pei, Hongming Zhang, Jiarui Guan, Jusheng Zhang, Liang Lin, Haogang Zhu, Ziliang Chen

Large language models (LLMs) are increasingly used as planners for cooperative embodied agents, but multi-agent settings amplify inconsistency under partial observability and make explicit communication costly or even unavailable. Many existing approaches rely on online message passing; when communication is removed, agents often fall back to independent local planning that suffers from tacit miscoordination. We introduce Contextual Tacit Communication, a training-free protocol that aligns decentralized decisions with a joint LLM value score without explicit message actions. Our method measures context-conditioned value rectifications via residual banding to pinpoint miscoordination actions and amortizes the resulting coordination signals into a retrieval-augmented Tacit Rule Memory that provides prompt-level cooperation rules at execution time. Experiments on VIKI, C-WAH, and TDW-MAT show that our approach improves cooperation performance over baselines while reducing runtime overhead compared with communication-based methods.

When Preference Labels Fall Short: Aligning Diffusion Models from Real Data

Weiyan Chen, Weijian Deng, Yao Xiao, Weijie Tu, ZiYi Dong, Ibrahim Radwan, Liang Lin, Pengxu Wei

Preference alignment aims to guide generative models by learning from comparisons between preferred and non-preferred samples. In practice, most existing approaches rely on preference pairs constructed from model-generated images. Such supervision is inherently relative and can be ambiguous when both samples exhibit artifacts or limited visual quality, making it difficult to infer what constitutes a truly desirable output. In this work, we investigate whether real data can serve as an alternative source of supervision for preference alignment. We adopt a data-centric perspective and study a curation strategy that treats real images as reference points and constructs preference signals by contrasting them with generated or perturbed samples, without requiring manually annotated preference pairs. Through empirical analysis, we show that real-data-based supervision provides effective guidance for aligning diffusion models and achieves performance comparable to existing preference-based methods. Our results suggest that real data offers a practical and complementary source of supervision for preference alignment and highlight directions of label-efficient alignment strategies.

3DGS-HPC: Distractor-free 3D Gaussian Splatting with Hybrid Patch-wise Classification

Jiahao Chen, Yipeng Qin, Ganlong Zhao, Xin Li, Wenping Wang, Guanbin Li

3D Gaussian Splatting (3DGS) has demonstrated remarkable performance in novel view synthesis and 3D scene reconstruction, but its quality often degrades in real-world environments due to transient distractors, such as moving objects and varying shadows. Existing methods commonly rely on semantic cues extracted from pre-trained vision models to identify and suppress these distractors, but such semantics are misaligned with the binary distinction between static and transient regions and remain fragile under the appearance perturbations introduced during 3DGS optimization. We propose 3DGS-HPC, a framework that circumvents these limitations by combining two complementary principles: a patch-wise classification strategy that leverages local spatial consistency for robust region-level decisions, and a hybrid classification metric that adaptively integrates photometric and perceptual cues for more reliable separation. Extensive experiments demonstrate the superiority and robustness of our method in mitigating distractors to improve 3DGS-based novel view synthesis. The code will be released.

CoF-T2I: Video Models as Pure Visual Reasoners for Text-to-Image Generation

Chengzhuo Tong, Mingkun Chang, Shenglong Zhang, Yuran Wang, Cheng Liang, Zhizheng Zhao, Bohan Zeng, Yang Shi, Ruichuan An, Yifan Dai, Ziming Zhao, Guanbin Li, Pengfei Wan, Yuanxing Zhang, Wentao Zhang

Recent video generation models have revealed the emergence of Chain-of-Frame (CoF) reasoning, enabling frame-by-frame visual inference. With this capability, video models have been successfully applied to various visual tasks (e.g., maze solving, visual puzzles). However, their potential to enhance text-to-image (T2I) generation remains largely unexplored due to the absence of a clearly defined visual reasoning starting point and interpretable intermediate states in the T2I generation process. To bridge this gap, we propose CoF-T2I, a model that integrates CoF reasoning into T2I generation via progressive visual refinement, where intermediate frames act as explicit reasoning steps and the final frame is taken as output. To establish such explicit generation process, we curate CoF-Evol-Instruct, a dataset of CoF trajectories that model the generation process from semantics to aesthetics. To further improve quality and avoid motion artifacts, we enable an independent encoding operation for each frame. Experiments show that CoF-T2I significantly outperforms the base video model and achieves competitive performance, reaching 0.86 on GenEval and 7.468 on Imagine-Bench. These results indicate the substantial promise of video models for advancing high-quality text-to-image generation.

Thinking with Geometry: Active Geometry Integration for Spatial Reasoning

Haoyuan Li, QihangCao, Tao Tang, Kun Xiang, Zihan Guo, Jianhua Han, Jia-Wang Bian, Hang Xu, Xiaodan Liang

Recent progress in spatial reasoning with Multimodal Large Language Models (MLLMs) increasingly leverages geometric priors from 3D encoders. However, most existing integration strategies remain passive: geometry is exposed as a global stream and fused in an indiscriminate manner, which often induces semantic-geometry misalignment and redundant signals. We propose GeoThinker, a framework that shifts the paradigm from passive fusion to active perception. Instead of feature mixing, GeoThinker enables the model to selectively retrieve geometric evidence conditioned on its internal reasoning demands. GeoThinker achieves this through Spatial-Grounded Fusion applied at carefully selected VLM layers, where semantic visual priors selectively query and integrate task-relevant geometry via frame-strict cross-attention, further calibrated by Importance Gating that biases per-frame attention toward task-relevant structures. Comprehensive evaluation results show that GeoThinker sets a new state-of-the-art in spatial intelligence, achieving a peak score of 72.6 on the VSI-Bench. Furthermore, GeoThinker demonstrates robust generalization and significantly improved spatial perception across complex downstream scenarios, including embodied referring and autonomous driving. Our results indicate that the ability to actively integrate spatial structures is essential for next-generation spatial intelligence.

Depth-Breadth Synergy in RLVR: Unlocking LLM Reasoning Gains with Adaptive Exploration

Zhicheng Yang, Zhijiang Guo, Yinya Huang, Yongxin Wang, Dongchun Xie, Hanhui Li, Yiwei Wang, Xiaodan Liang, Jing Tang

Reinforcement Learning with Verifiable Reward (RLVR) is a powerful method for enhancing the reasoning abilities of Large Language Models, but its full potential is limited by a lack of exploration in two key areas: \textbf{Depth} (the difficulty of problems) and \textbf{Breadth} (the number of training instances). Our analysis of the popular GRPO algorithm reveals a bias that down-weights difficult, low-accuracy problems, which are crucial for improving reasoning skills. To address this, we introduce Difficulty Adaptive Rollout Sampling (DARS), a method that re-weights difficult problems by using targeted, multi-stage rollouts. This approach increases the number of rollout outcomes for these harder problems according to our proposed re-balancing schedules and leads to consistent gains in \textit{Pass@K}. We also found that simply enlarging the rollout size isn't effective and can even harm performance. We also investigated the role of breadth by scaling the batch size and using full-batch updates. This significantly improved \textit{Pass@1} performance by maintaining high token-level entropy, which indicates continued exploration and reduced gradient noise. Finally, we present DARS-Breadth, a combined approach that uses DARS with a large breadth of training data. This method demonstrates simultaneous gains in both \textit{Pass@K} and \textit{Pass@1}, confirming that depth (adaptive exploration) and breadth (scaling the training data) are orthogonal and essential dimensions for unlocking the full reasoning power of RLVR.

Accordion-Thinking: Self-Regulated Step Summaries for Efficient and Readable LLM Reasoning

Zhicheng Yang, Zhijiang Guo, Yinya Huang, Yongxin Wang, Wenlei Shi, Yiwei Wang, Xiaodan Liang, Jing Tang

Scaling test-time compute via long Chain-of-Thought unlocks remarkable gains in reasoning capabilities, yet it faces practical limits due to the linear growth of KV cache and quadratic attention complexity. In this paper, we introduce AccordionThinking, an end-to-end framework where LLMs learn to self-regulate the granularity of the reasoning steps through dynamic summarization. This mechanism enables a Fold inference mode, where the model periodically summarizes its thought process and discards former thoughts to reduce dependency on historical tokens. We apply reinforcement learning to incentivize this capability further, uncovering a critical insight: the accuracy gap between the highly efficient Fold mode and the exhaustive Unfold mode progressively narrows and eventually vanishes over the course of training. This phenomenon demonstrates that the model learns to encode essential reasoning information into compact summaries, achieving effective compression of the reasoning context. Our AccordionThinker demonstrates that with learned self-compression, LLMs can tackle complex reasoning tasks with minimal dependency token overhead without compromising solution quality, and it achieves a 3× throughput while maintaining accuracy on a 48GB GPU memory configuration, while the structured step summaries provide a human-readable account of the reasoning process.

iTryOn: Mastering Interactive Video Virtual Try-On with Spatial-Semantic Guidance

Jun Zheng, Zhengze Xu, Mengting Chen, Jing Wang, Jinsong Lan, Xiaoyong Zhu, Kaifu Zhang, Bo Zheng, Xiaodan Liang

Video Virtual Try-On (VVT) aims to seamlessly replace a garment on a person in a video with a new one. While existing methods have made significant strides in maintaining temporal consistency, they are predominantly confined to non-interactive scenarios where models merely showcase garments. This limitation overlooks a crucial aspect of real-world apparel presentation: active human-garment interaction. To bridge this gap, we introduce and formalize a new challenging task: Interactive Video Virtual Try-On (Interactive VVT), where subjects in the video actively engage with their clothing (e.g., pulling a hem or unzipping a jacket). This task introduces unique challenges beyond simple texture preservation, including: (1) resolving the semantic ambiguity of interactions from standard pose information, and (2) learning complex garment deformations from video where interactive moments are sparse and brief. To address these challenges, we propose iTryOn, a novel framework built upon a large-scale video diffusion Transformer. iTryOn pioneers a multi-level interaction injection mechanism to guide the generation of complex dynamics. At the spatial level, we introduce a garment-agnostic 3D hand prior to provide fine-grained guidance for precise hand-garment contact, effectively resolving spatial ambiguity. At the semantic level, iTryOn leverages global captions for overall context and time-stamped action captions for localized interactions, synchronized via our novel Action-aware Rotational Position Embedding (A-RoPE). Furthermore, we design an action-aware constraint loss to stabilize training and focus the learning process on these critical interactive frames. To facilitate research and evaluation, we construct VVT-Interact, the first large-scale dataset for this task , and propose a novel interaction-aware evaluation metric to quantify the semantic fidelity of interactions. Extensive experiments demonstrate that iTryOn not only achieves state-of-the-art performance on traditional VVT benchmarks but also establishes a commanding lead in the new interactive setting, marking a significant step towards more dynamic

and controllable virtual try-on experiences.