Wenhao Zhang

Lu Yi, Runlin Lei, Liuyi Yao et al.

LLM agents increasingly face long-horizon tasks such as web search and deep research in real-world applications, where accumulated context can cause long-context degradation and reasoning failures. Prior work mitigates this through context management with agent-side context control or fixed strategies such as summarization, which require training the agent itself for adaptation - making it impractical for closed-source agents and ignoring that different agents may require different strategies. We introduce Adaptive Context Management (AdaCoM), which trains an external LLM to manage the context of a frozen agent through flexible modification actions and end-to-end reinforcement learning. Across diverse agents on web search and deep research benchmarks, AdaCoM substantially improves performance by preserving task constraints and progress while pruning stale content. The learned strategies reveal a Fidelity-Reliability Trade-off: agents with higher vanilla ReAct performance benefit from higher-fidelity context preservation, whereas lower-performing agents require more aggressive compression to stay within a reliable reasoning regime. Transfer experiments show that AdaCoM generalizes most effectively across agents with similar capability (measured by vanilla ReAct performance), suggesting a practical path toward reusable context managers for agent systems.

Yunzhong Si, Huiying Xu, Xinzhong Zhu et al.

Channel and spatial attentions have respectively brought significant improvements in extracting feature dependencies and spatial structure relations for various downstream vision tasks. While their combination is more beneficial for leveraging their individual strengths, the synergy between channel and spatial attentions has not been fully explored, lacking in fully harness the synergistic potential of multi-semantic information for feature guidance and mitigation of semantic disparities. Our study attempts to reveal the synergistic relationship between spatial and channel attention at multiple semantic levels, proposing a novel Spatial and Channel Synergistic Attention module (SCSA). Our SCSA consists of two parts: the Shareable Multi-Semantic Spatial Attention (SMSA) and the Progressive Channel-wise Self-Attention (PCSA). SMSA integrates multi-semantic information and utilizes a progressive compression strategy to inject discriminative spatial priors into PCSA's channel self-attention, effectively guiding channel recalibration. Additionally, the robust feature interactions based on the self-attention mechanism in PCSA further mitigate the disparities in multi-semantic information among different sub-features within SMSA. We conduct extensive experiments on seven benchmark datasets, including classification on ImageNet-1K, object detection on MSCOCO 2017, segmentation on ADE20K, and four other complex scene detection datasets. Our results demonstrate that our proposed SCSA not only surpasses the current state-of-the-art attention but also exhibits enhanced generalization capabilities across various task scenarios. The code and models are available at: https://github.com/HZAI-ZJNU/SCSA.

Hongbo Jin, Qingyuan Wang, Wenhao Zhang et al. · tsinghua

Ultra long video understanding remains an open challenge, as existing vision language models (VLMs) falter on such content due to limited context length and inefficient long term memory retention. To address this, recent works have attempted to construct external knowledge bases and corresponding retrieval agumented generation (RAG) systems, yet these incur enormous storage and computational overhead. In this paper, we propose VideoMem, a novel framework that pioneers models long video understanding as a sequential generation task via adaptive memory management. Specifically, VideoMem dynamically updates a global memory buffer, which adaptively retains critical information while discarding redundant content across the video timeline. To efficiently train VLMs for such long-term tasks, VideoMem integrates the Progressive Grouped Relative Policy Optimization (PRPO) algorithm, equipped with two core modules: Progressive State Propagation (PSP) adaptively retains valid current states, propagates them to the next rollout step, and gradually narrows the model exploration space. Temporal Cascading Reward (TCR) further alleviates reward sparsity, improving sample utilization and accelerating convergence. Extensive experiments demonstrate that VideoMem significantly outperforms existing open-source models across diverse benchmarks for ultra-long video understanding tasks.

Zhen Qin, Daoyuan Chen, Wenhao Zhang et al.

The rapid development of large language models (LLMs) has been witnessed in recent years. Based on the powerful LLMs, multi-modal LLMs (MLLMs) extend the modality from text to a broader spectrum of domains, attracting widespread attention due to the broader range of application scenarios. As LLMs and MLLMs rely on vast amounts of model parameters and data to achieve emergent capabilities, the importance of data is receiving increasingly widespread attention and recognition. Tracing and analyzing recent data-oriented works for MLLMs, we find that the development of models and data is not two separate paths but rather interconnected. On the one hand, vaster and higher-quality data contribute to better performance of MLLMs; on the other hand, MLLMs can facilitate the development of data. The co-development of multi-modal data and MLLMs requires a clear view of 1) at which development stages of MLLMs specific data-centric approaches can be employed to enhance certain MLLM capabilities, and 2) how MLLMs, utilizing those capabilities, can contribute to multi-modal data in specific roles. To promote the data-model co-development for MLLM community, we systematically review existing works related to MLLMs from the data-model co-development perspective. A regularly maintained project associated with this survey is accessible at https://github.com/modelscope/data-juicer/blob/main/docs/awesome_llm_data.md.

Xihuai Wang, Shao Zhang, Wenhao Zhang et al.

Zero-shot coordination (ZSC) is a new cooperative multi-agent reinforcement learning (MARL) challenge that aims to train an ego agent to work with diverse, unseen partners during deployment. The significant difference between the deployment-time partners' distribution and the training partners' distribution determined by the training algorithm makes ZSC a unique out-of-distribution (OOD) generalization challenge. The potential distribution gap between evaluation and deployment-time partners leads to inadequate evaluation, which is exacerbated by the lack of appropriate evaluation metrics. In this paper, we present ZSC-Eval, the first evaluation toolkit and benchmark for ZSC algorithms. ZSC-Eval consists of: 1) Generation of evaluation partner candidates through behavior-preferring rewards to approximate deployment-time partners' distribution; 2) Selection of evaluation partners by Best-Response Diversity (BR-Div); 3) Measurement of generalization performance with various evaluation partners via the Best-Response Proximity (BR-Prox) metric. We use ZSC-Eval to benchmark ZSC algorithms in Overcooked and Google Research Football environments and get novel empirical findings. We also conduct a human experiment of current ZSC algorithms to verify the ZSC-Eval's consistency with human evaluation. ZSC-Eval is now available at https://github.com/sjtu-marl/ZSC-Eval.

Minh Cao, Tianqi Zhao, Yanxun Li et al.

Electrocardiogram (ECG) is a simple non-invasive measure to identify heart-related issues such as irregular heartbeats known as arrhythmias. While artificial intelligence and machine learning is being utilized in a wide range of healthcare related applications and datasets, many arrhythmia classifiers using deep learning methods have been proposed in recent years. However, sizes of the available datasets from which to build and assess machine learning models is often very small and the lack of well-annotated public ECG datasets is evident. In this paper, we propose a deep transfer learning framework that is aimed to perform classification on a small size training dataset. The proposed method is to fine-tune a general-purpose image classifier ResNet-18 with MIT-BIH arrhythmia dataset in accordance with the AAMI EC57 standard. This paper further investigates many existing deep learning models that have failed to avoid data leakage against AAMI recommendations. We compare how different data split methods impact the model performance. This comparison study implies that future work in arrhythmia classification should follow the AAMI EC57 standard when using any including MIT-BIH arrhythmia dataset.

Yi Bai, Wenhao Zhang, Yao Chen et al.

Instruction fine-tuning is employed to enhance the instruction-following ability of large language models (LLMs). As the amount of instruction fine-tuning data increases, selecting the optimal core set becomes particularly important. However, ensuring the diversity of the core set remains a significant challenge. Existing methods predominantly distinguish different training data based on the text features themselves, decoupled from LLMs' own understanding and representation of the data. To address this issue, we propose a Model-Aware Diverse Core Set Selection method, which distinguishes data features based on the neural activation states during LLM inference. This approach serves as an efficient instantiation of coverage-based selection using model-intrinsic activation features to ensure the diversity in the core set. We extensively evaluate our method on six benchmarks that cover five distinct tasks. In our method, the core set selected by the 3B-parameter LLM performs effectively when utilized to fine-tune larger models with 7B, 8B, and 13B parameters. Experimental results on the Alpaca-GPT4 dataset, which comprises 52K instruction-response pairs, show that the core set, sized at 15\% of the original dataset and selected by Llama-3.2-3B-Instruct, achieves an average improvement of 2.5\% when fine-tuning four larger base models compared with training on the full dataset. The experimental results demonstrate that our method enhances model performance on multiple downstream tasks while reducing data requirements.

Yang Li, Shao Zhang, Jichen Sun et al.

Securing coordination between AI agent and teammates (human players or AI agents) in contexts involving unfamiliar humans continues to pose a significant challenge in Zero-Shot Coordination. The issue of cooperative incompatibility becomes particularly prominent when an AI agent is unsuccessful in synchronizing with certain previously unknown partners. Traditional algorithms have aimed to collaborate with partners by optimizing fixed objectives within a population, fostering diversity in strategies and behaviors. However, these techniques may lead to learning loss and an inability to cooperate with specific strategies within the population, a phenomenon named cooperative incompatibility in learning. In order to solve cooperative incompatibility in learning and effectively address the problem in the context of ZSC, we introduce the Cooperative Open-ended LEarning (COLE) framework, which formulates open-ended objectives in cooperative games with two players using perspectives of graph theory to evaluate and pinpoint the cooperative capacity of each strategy. We present two practical algorithms, specifically \algo and \algoR, which incorporate insights from game theory and graph theory. We also show that COLE could effectively overcome the cooperative incompatibility from theoretical and empirical analysis. Subsequently, we created an online Overcooked human-AI experiment platform, the COLE platform, which enables easy customization of questionnaires, model weights, and other aspects. Utilizing the COLE platform, we enlist 130 participants for human experiments. Our findings reveal a preference for our approach over state-of-the-art methods using a variety of subjective metrics. Moreover, objective experimental outcomes in the Overcooked game environment indicate that our method surpasses existing ones when coordinating with previously unencountered AI agents and the human proxy model.

Wenhao Zhang, Lin Mu, Li Ni et al.

Low-rank adaptation (LoRA) is a widely used strategy for efficient fine-tuning of large language models (LLMs), but its strictly linear structure fundamentally limits expressive capacity. The bilinear formulation of weight updates captures only first-order dependencies between low-rank factors, restricting the modeling of nonlinear and higher-order parameter interactions. In this paper, we propose Polynomial Expansion Rank Adaptation (PERA), a novel method that introduces structured polynomial expansion directly into the low-rank factor space. By expanding each low-rank factor to synthesize high-order interaction terms before composition, PERA transforms the adaptation space into a polynomial manifold capable of modeling richer nonlinear coupling without increasing rank or inference cost. We provide theoretical analysis demonstrating that PERA offers enhanced expressive capacity and more effective feature utilization compare to existing linear adaptation approaches. Empirically, PERA consistently outperforms state-of-the-art methods across diverse benchmarks. Notably, our experiments show that incorporating high-order nonlinear components particularly square terms is crucial for enhancing expressive capacity and maintaining strong and robust performance under various rank settings. Our code is available at https://github.com/zhangwenhao6/PERA

Shao Zhang, Xihuai Wang, Wenhao Zhang et al.

Theory of Mind (ToM) significantly impacts human collaboration and communication as a crucial capability to understand others. When AI agents with ToM capability collaborate with humans, Mutual Theory of Mind (MToM) arises in such human-AI teams (HATs). The MToM process, which involves interactive communication and ToM-based strategy adjustment, affects the team's performance and collaboration process. To explore the MToM process, we conducted a mixed-design experiment using a large language model-driven AI agent with ToM and communication modules in a real-time shared-workspace task. We find that the agent's ToM capability does not significantly impact team performance but enhances human understanding of the agent and the feeling of being understood. Most participants in our study believe verbal communication increases human burden, and the results show that bidirectional communication leads to lower HAT performance. We discuss the results' implications for designing AI agents that collaborate with humans in real-time shared workspace tasks.

Dawei Gao, Zitao Li, Xuchen Pan et al.

With the rapid advancement of Large Language Models (LLMs), significant progress has been made in multi-agent applications. However, the complexities in coordinating agents' cooperation and LLMs' erratic performance pose notable challenges in developing robust and efficient multi-agent applications. To tackle these challenges, we propose AgentScope, a developer-centric multi-agent platform with message exchange as its core communication mechanism. The abundant syntactic tools, built-in agents and service functions, user-friendly interfaces for application demonstration and utility monitor, zero-code programming workstation, and automatic prompt tuning mechanism significantly lower the barriers to both development and deployment. Towards robust and flexible multi-agent application, AgentScope provides both built-in and customizable fault tolerance mechanisms. At the same time, it is also armed with system-level support for managing and utilizing multi-modal data, tools, and external knowledge. Additionally, we design an actor-based distribution framework, enabling easy conversion between local and distributed deployments and automatic parallel optimization without extra effort. With these features, AgentScope empowers developers to build applications that fully realize the potential of intelligent agents. We have released AgentScope at https://github.com/modelscope/agentscope, and hope AgentScope invites wider participation and innovation in this fast-moving field.

Shiao Wang, Xiao Wang, Duoqing Yang et al.

Despite significant progress, RGB-based trackers remain vulnerable to challenging imaging conditions, such as low illumination and fast motion. Event cameras offer a promising alternative by asynchronously capturing pixel-wise brightness changes, providing high dynamic range and high temporal resolution. However, existing event-based trackers often neglect the intrinsic spatial sparsity and temporal density of event data, while relying on a single fixed temporal-window sampling strategy that is suboptimal under varying motion dynamics. In this paper, we propose an event sparsity-aware tracking framework that explicitly models event-density variations across multiple temporal scales. Specifically, the proposed framework progressively injects sparse, medium-density, and dense event search regions into a three-stage Vision Transformer backbone, enabling hierarchical multi-density feature learning. Furthermore, we introduce a sparsity-aware Mixture-of-Experts module to encourage expert specialization under different sparsity patterns, and design a dynamic pondering strategy to adaptively adjust the inference depth according to tracking difficulty. Extensive experiments on FE240hz, COESOT, and EventVOT demonstrate that the proposed approach achieves a favorable trade-off between tracking accuracy and computational efficiency. The source code will be released on https://github.com/Event-AHU/OpenEvTracking.

Wenhao Zhang, Ruihao Yu, Yi Bai et al.

While generative retrieval (GR) demonstrates competitive performance on standard retrieval benchmarks, existing approaches directly map queries to document identifiers (docids) without intermediate deliberation, limiting their effectiveness for complex queries that require multi-step reasoning. As a preliminary study on integrating chain-of-thought (CoT) into generative retrieval, we introduce ThinkGR, a unified framework that interleaves CoT with docid generation, enabling iterative thinking and retrieval within a single generative process. To bridge the gap between free-form thought generation and structured retrieval targets, we design (1) a hybrid decoding strategy that dynamically switches between unconstrained thought generation and constrained docid decoding, and (2) a two-phase training approach that first aligns thought-retrieval patterns through supervised fine-tuning, then optimizes thought quality via retrieval-grounded reinforcement learning. Experiments on four multi-hop retrieval benchmarks demonstrate that ThinkGR achieves state-of-the-art performance with an average improvement of +6.86\%. Our work opens new avenues for enhancing generative retrieval with explicit deliberation capabilities, with promising implications for retrieval tasks requiring complex reasoning.

Kuanwei Lin, Wenhao Zhang, Ge Li

Video large multimodal models increasingly face a scalability bottleneck: long videos produce excessively long visual-token sequences, which sharply increase memory and latency during inference. While existing compression methods are effective in specific settings, most are either weakly query-aware or apply a fixed compression policy across frames, proving suboptimal when visual evidence is unevenly distributed over time. To address this, we present VideoRouter, a query-adaptive dual-router framework built on InternVL for budgeted evidence allocation. The Semantic Router predicts the dominant allocation policy, choosing between broad temporal coverage and adaptive high-resolution preservation, while the Image Router uses early LLM layers to score frame relevance. This enables aggressive compression on less relevant frames while preserving detail on critical evidence frames. To train both routers, we build Video-QTR-10K for allocation-policy supervision and Video-FLR-200K for frame-relevance supervision. Experiments on VideoMME, MLVU, and LongVideoBench show that VideoRouter consistently improves over the InternVL baseline under comparable or lower budgets, achieving up to a 67.9% token reduction.

Shumin Wang, Yuexiang Xie, Wenhao Zhang et al.

Entropy serves as a critical metric for measuring the diversity of outputs generated by large language models (LLMs), providing valuable insights into their exploration capabilities. While recent studies increasingly focus on monitoring and adjusting entropy to better balance exploration and exploitation in reinforcement fine-tuning (RFT), a principled understanding of entropy dynamics during this process is yet to be thoroughly investigated. In this paper, we establish a theoretical framework for analyzing the entropy dynamics during the RFT process, which begins with a discriminant expression that quantifies entropy change under a single logit update. This foundation enables the derivation of a first-order expression for entropy change, which can be further extended to the update formula of Group Relative Policy Optimization (GRPO). The corollaries and insights drawn from the theoretical analysis inspire the design of entropy control methods, and also offer a unified lens for interpreting various entropy-based methods in existing studies. We provide empirical evidence to support the main conclusions of our analysis and demonstrate the effectiveness of the derived entropy-discriminator clipping methods. This study yields novel insights into RFT training dynamics, providing theoretical support and practical strategies for optimizing the exploration-exploitation balance during LLM fine-tuning.

Wenhao Zhang, Yuexiang Xie, Yuchang Sun et al.

Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL) are two prominent post-training paradigms for refining the capabilities and aligning the behavior of Large Language Models (LLMs). Existing approaches that integrate SFT and RL often face the risk of disrupting established response patterns and inducing overfitting to expert data. To address this, we present a novel investigation into the unified view of SFT and RL through an off-policy versus on-policy lens. We propose CHORD, a framework for Controllable Harmonization of On- and Off-Policy Reinforcement Learning via Dynamic Weighting, which reframes SFT not as a separate stage but as a dynamically weighted auxiliary objective within the on-policy RL process. Based on an analysis of off-policy expert data's influence at both holistic and granular levels, we incorporate a dual-control mechanism in CHORD. Specifically, the framework first employs a global coefficient to holistically guide the transition from off-policy imitation to on-policy exploration, and then applies a token-wise weighting function that enables granular learning from the expert, which promotes on-policy exploration and mitigates disruption from off-policy data. We conduct extensive experiments on mathematical reasoning problems and practical tool-use tasks, providing empirical evidence that CHORD achieves a stable and efficient learning process. By effectively harmonizing off-policy expert data with on-policy exploration, CHORD demonstrates significant improvements over baselines. We release the implementation at https://github.com/modelscope/Trinity-RFT/tree/main/examples/mix_chord to inspire further research.

Haohao Luo, Zexi Li, Yuexiang Xie et al.

Deep Research (DR) agents extend Large Language Models (LLMs) beyond parametric knowledge by autonomously retrieving and synthesizing evidence from large web corpora into long-form reports, enabling a long-horizon agentic paradigm. However, unlike real-time conversational assistants, DR is computationally expensive and time-consuming, creating an autonomy-interaction dilemma: high autonomy on ambiguous user queries often leads to prolonged execution with unsatisfactory outcomes. To address this, we propose IntentRL, a framework that trains proactive agents to clarify latent user intents before starting long-horizon research. To overcome the scarcity of open-ended research data, we introduce a scalable pipeline that expands a few seed samples into high-quality dialogue turns via a shallow-to-deep intent refinement graph. We further adopt a two-stage reinforcement learning (RL) strategy: Stage I applies RL on offline dialogues to efficiently learn general user-interaction behavior, while Stage II uses the trained agent and a user simulator for online rollouts to strengthen adaptation to diverse user feedback. Extensive experiments show that IntentRL significantly improves both intent hit rate and downstream task performance, outperforming the built-in clarify modules of closed-source DR agents and proactive LLM baselines.

YuAn Wang, Xiaofan Li, Chi Huang et al.

In controllable driving-scene reconstruction and 3D scene generation, maintaining geometric fidelity while synthesizing visually plausible appearance under large viewpoint shifts is crucial. However, effective fusion of geometry-based 3DGS and appearance-driven diffusion models faces inherent challenges, as the absence of pixel-wise, 3D-consistent editing criteria often leads to over-restoration and geometric drift. To address these issues, we introduce \textbf{FaithFusion}, a 3DGS-diffusion fusion framework driven by pixel-wise Expected Information Gain (EIG). EIG acts as a unified policy for coherent spatio-temporal synthesis: it guides diffusion as a spatial prior to refine high-uncertainty regions, while its pixel-level weighting distills the edits back into 3DGS. The resulting plug-and-play system is free from extra prior conditions and structural modifications.Extensive experiments on the Waymo dataset demonstrate that our approach attains SOTA performance across NTA-IoU, NTL-IoU, and FID, maintaining an FID of 107.47 even at 6 meters lane shift. Our code is available at https://github.com/wangyuanbiubiubiu/FaithFusion.

Shao Zhang, Xihuai Wang, Wenhao Zhang et al.

Agents built on large language models (LLMs) have excelled in turn-by-turn human-AI collaboration but struggle with simultaneous tasks requiring real-time interaction. Latency issues and the challenge of inferring variable human strategies hinder their ability to make autonomous decisions without explicit instructions. Through experiments with current independent System 1 and System 2 methods, we validate the necessity of using Dual Process Theory (DPT) in real-time tasks. We propose DPT-Agent, a novel language agent framework that integrates System 1 and System 2 for efficient real-time simultaneous human-AI collaboration. DPT-Agent's System 1 uses a Finite-state Machine (FSM) and code-as-policy for fast, intuitive, and controllable decision-making. DPT-Agent's System 2 integrates Theory of Mind (ToM) and asynchronous reflection to infer human intentions and perform reasoning-based autonomous decisions. We demonstrate the effectiveness of DPT-Agent through further experiments with rule-based agents and human collaborators, showing significant improvements over mainstream LLM-based frameworks. DPT-Agent can effectively help LLMs convert correct slow thinking and reasoning into executable actions, thereby improving performance. To the best of our knowledge, DPT-Agent is the first language agent framework that achieves successful real-time simultaneous human-AI collaboration autonomously. Code of DPT-Agent can be found in https://github.com/sjtu-marl/DPT-Agent.

Chaorui Yao, Yanxi Chen, Yuchang Sun et al.

Off-policy reinforcement learning (RL) for large language models (LLMs) is attracting growing interest, driven by practical constraints in real-world applications, the complexity of LLM-RL infrastructure, and the need for further innovations of RL methodologies. While classic REINFORCE and its modern variants like Group Relative Policy Optimization (GRPO) are typically regarded as on-policy algorithms with limited tolerance of off-policyness, we present in this work a first-principles derivation for group-relative REINFORCE without assuming a specific training data distribution, showing that it admits a native off-policy interpretation. This perspective yields two general principles for adapting REINFORCE to off-policy settings: regularizing policy updates, and actively shaping the data distribution. Our analysis demystifies some myths about the roles of importance sampling and clipping in GRPO, unifies and reinterprets two recent algorithms -- Online Policy Mirror Descent (OPMD) and Asymmetric REINFORCE (AsymRE) -- as regularized forms of the REINFORCE loss, and offers theoretical justification for seemingly heuristic data-weighting strategies. Our findings lead to actionable insights that are validated with extensive empirical studies, and open up new opportunities for principled algorithm design in off-policy RL for LLMs. Source code for this work is available at https://github.com/modelscope/Trinity-RFT/tree/main/examples/rec_gsm8k.

Hongbo Jin, Ruyang Liu, Wenhao Zhang et al.

System2 reasoning is developing rapidly these days with the emergence of Deep- Thinking Models and chain-of-thought technology, which has become a centralized discussion point in the AI community. However, there is a relative gap in the research on complex video reasoning at present. In this work, we propose CoT-Vid, a novel training-free paradigm for the video domain with a multistage complex reasoning design. Distinguishing from existing video LLMs, which rely heavily on perceptual abilities, it achieved surprising performance gain with explicit reasoning mechanism. The paradigm consists of three main components: dynamic inference path routing, problem decoupling strategy, and video self-consistency verification. In addition, we propose a new standard for categorization of video questions. CoT- Vid showed outstanding results on a wide range of benchmarks, and outperforms its base model by 9.3% on Egochema and 5.6% on VideoEspresso, rivalling or even surpassing larger and proprietary models, such as GPT-4V, GPT-4o and Gemini-1.5-flash. Our codebase will be publicly available soon.

Wenhao Zhang, Shao Zhang, Xihuai Wang et al.

In-Context Reinforcement Learning (ICRL) has emerged as a promising paradigm for developing agents that can rapidly adapt to new tasks by leveraging past experiences as context, without updating their parameters. Recent approaches train large sequence models on monotonic policy improvement data from online RL, aiming to a continue improved testing time performance. However, our experimental analysis reveals a critical flaw: these models cannot show a continue improvement like the training data during testing time. Theoretically, we identify this phenomenon as Contextual Ambiguity, where the model's own stochastic actions can generate an interaction history that misleadingly resembles that of a sub-optimal policy from the training data, initiating a vicious cycle of poor action selection. To resolve the Contextual Ambiguity, we introduce Context Value into training phase and propose Context Value Informed ICRL (CV-ICRL). CV-ICRL use Context Value as an explicit signal representing the ideal performance theoretically achievable by a policy given the current context. As the context expands, Context Value could include more task-relevant information, and therefore the ideal performance should be non-decreasing. We prove that the Context Value tightens the lower bound on the performance gap relative to an ideal, monotonically improving policy. We fruther propose two methods for estimating Context Value at both training and testing time. Experiments conducted on the Dark Room and Minigrid testbeds demonstrate that CV-ICRL effectively mitigates performance degradation and improves overall ICRL abilities across various tasks and environments. The source code and data of this paper are available at https://github.com/Bluixe/towards_monotonic_improvement .

Jiaqi Wang, Wenhao Zhang, Weijie Shi et al.

On-policy distillation (OPD) has shown strong potential for transferring reasoning ability from frontier or domain-specific models to smaller students. While effective on static single-turn tasks, its behavior in multi-turn agent settings remains underexplored. In this work, we identify a key limitation of vanilla OPD in such settings, which we term Trajectory-Level KL Instability. Specifically, we observe that KL divergence increases together with a drop in success rate, and even after convergence, the KL remains high, leading to unstable training. This instability arises from inter-turn error compounding: as errors accumulate, the student is driven beyond the teacher's effective support, rendering the supervision signal unreliable. To address this, we propose TCOD (Temporal Curriculum On-Policy Distillation), a simple yet effective framework that controls the trajectory depth exposed to the student and progressively expands it from short to long with a curriculum schedule.Experimental results across four student-teacher pairs on three multi-turn agent benchmarks (ALFWorld, WebShop, ScienceWorld) show that TCOD mitigates KL escalation and enhances KL stability throughout training, improving agent performance by up to 18 points over vanilla OPD. Further evaluations show that TCOD can even surpass the teacher's performance and generalize to tasks on which the teacher fails.

Hongbo Jin, Rongpeng Zhu, Jiayu Ding et al.

Large language model (LLM) agents have recently demonstrated strong capabilities in interactive decision-making, yet they remain fundamentally limited in long-horizon tasks that require structured planning and reliable execution. Existing approaches predominantly rely on flat autoregressive policies, where high-level reasoning and low-level actions are generated within a single token sequence, leading to inefficient exploration and severe error propagation over extended trajectories. In this work, we propose HiMAC, a hierarchical agentic RL framework that explicitly decomposes long-horizon decision-making into macro-level planning and micro-level execution. HiMAC models reasoning as a structured blueprint generation process followed by goal-conditioned action execution, enabling robust long-horizon planning within LLM-based agents. To train this hierarchy efficiently, we introduce a critic-free hierarchical policy optimization paradigm that extends group-based reinforcement learning to bi-level structures through hierarchical relative advantage estimation. Furthermore, we propose an iterative co-evolution training strategy that alternates between planner exploration and executor adaptation, mitigating the non-stationarity inherent in hierarchical learning. Extensive experiments on ALFWorld, WebShop, and Sokoban demonstrate that HiMAC consistently outperforms strong prompting and reinforcement learning baselines, achieving state-of-the-art performance and substantially improved sample efficiency across both text-based and visually grounded environments. Our results show that introducing structured hierarchy, rather than increasing model scale alone, is a key factor for enabling robust long-horizon agentic intelligence.

Yang Li, Wenhao Zhang, Jianhong Wang et al.

Among the research topics in multi-agent learning, mixed-motive cooperation is one of the most prominent challenges, primarily due to the mismatch between individual and collective goals. The cutting-edge research is focused on incorporating domain knowledge into rewards and introducing additional mechanisms to incentivize cooperation. However, these approaches often face shortcomings such as the effort on manual design and the absence of theoretical groundings. To close this gap, we model the mixed-motive game as a differentiable game for the ease of illuminating the learning dynamics towards cooperation. More detailed, we introduce a novel optimization method named \textbf{\textit{A}}ltruistic \textbf{\textit{G}}radient \textbf{\textit{A}}djustment (\textbf{\textit{AgA}}) that employs gradient adjustments to progressively align individual and collective objectives. Furthermore, we theoretically prove that AgA effectively attracts gradients to stable fixed points of the collective objective while considering individual interests, and we validate these claims with empirical evidence. We evaluate the effectiveness of our algorithm AgA through benchmark environments for testing mixed-motive collaboration with small-scale agents such as the two-player public good game and the sequential social dilemma games, Cleanup and Harvest, as well as our self-developed large-scale environment in the game StarCraft II.

Hongbo Jin, Kuanwei Lin, Wenhao Zhang et al.

Reinforcement Learning (RL) is crucial for empowering VideoLLMs with complex spatiotemporal reasoning. However, current RL paradigms predominantly rely on random data shuffling or naive curriculum strategies based on scalar difficulty metrics. We argue that scalar metrics fail to disentangle two orthogonal challenges in video understanding: Visual Temporal Perception Load and Cognitive Reasoning Depth. To address this, we propose VideoCuRL, a novel framework that decomposes difficulty into these two axes. We employ efficient, training-free proxies, optical flow and keyframe entropy for visual complexity, Calibrated Surprisal for cognitive complexity, to map data onto a 2D curriculum grid. A competence aware Diagonal Wavefront strategy then schedules training from base alignment to complex reasoning. Furthermore, we introduce Dynamic Sparse KL and Structured Revisiting to stabilize training against reward collapse and catastrophic forgetting. Extensive experiments show that VideoCuRL surpasses strong RL baselines on reasoning (+2.5 on VSI-Bench) and perception (+2.9 on VideoMME) tasks. Notably, VideoCuRL eliminates the prohibitive inference overhead of generation-based curricula, offering a scalable solution for robust video post-training.

Xuchen Pan, Yanxi Chen, Yushuo Chen et al.

Trinity-RFT is a general-purpose, unified and easy-to-use framework designed for reinforcement fine-tuning (RFT) of large language models. It is built with a modular and decoupled design, consisting of (1) an RFT-core that unifies and generalizes synchronous/asynchronous, on-policy/off-policy, and online/offline modes of RFT; (2) seamless integration for agent-environment interaction with high efficiency and robustness; and (3) systematic data pipelines optimized for RFT. Trinity-RFT can be easily adapted for diverse application scenarios, and serves as a unified platform for development and research of advanced reinforcement learning paradigms at both macroscopic and microscopic levels. This technical report outlines the vision, features, design and implementations of Trinity-RFT, accompanied by extensive examples, applications and experiments that demonstrate its functionalities and user-friendliness.

Daoyuan Chen, Yilun Huang, Xuchen Pan et al.

Foundation models demand advanced data processing for their vast, multimodal datasets. However, traditional frameworks struggle with the unique complexities of multimodal data. In response, we present Data-Juicer 2.0, a data processing system backed by 100+ data processing operators spanning text, image, video, and audio modalities, supporting more critical tasks including data analysis, synthesis, annotation, and foundation model post-training. With seamless compatibility and dedicated optimization for popular dataset hubs like Hugging Face and computing engines like Ray, it improves upon its predecessor in terms of usability, efficiency, and programmability. It features an easily accessible user interface layer that supports decoupled Python interactions, RESTful APIs, and conversational commands. Its new runtime layer offers adaptive execution across diverse scales and environments, abstracting away system complexities. Extensive empirical evaluations demonstrate Data-Juicer 2.0's remarkable performance and scalability, highlighting its capability to efficiently process TB-level data with 10k+ CPU cores. The system is publicly available and has been widely adopted in diverse research fields and real-world products such as Alibaba Cloud PAI. We actively maintain the system and share practical insights to foster research and applications of next-generation foundation models.

Wenhao Zhang, Matias Quintana, Clayton Miller

The indoor environment significantly impacts human health and well-being; enhancing health and reducing energy consumption in these settings is a central research focus. With the advancement of Information and Communication Technology (ICT), recommendation systems and reinforcement learning (RL) have emerged as promising approaches to induce behavioral changes to improve the indoor environment and energy efficiency of buildings. This study aims to employ text mining and Natural Language Processing (NLP) techniques to thoroughly examine the connections among these approaches in the context of human-building interaction and occupant context-aware support. The study analyzed 27,595 articles from the ScienceDirect database, revealing extensive use of recommendation systems and RL for space optimization, location recommendations, and personalized control suggestions. Furthermore, this review underscores the vast potential for expanding recommender systems and RL applications in buildings and indoor environments. Fields ripe for innovation include predictive maintenance, building-related product recommendation, and optimization of environments tailored for specific needs, such as sleep and productivity enhancements based on user feedback. The study also notes the limitations of the method in capturing subtle academic nuances. Future improvements could involve integrating and fine-tuning pre-trained language models to better interpret complex texts.

Pu Li, Wenhao Zhang, Jianwei Guo et al.

The integration of deep generative networks into generating Computer-Aided Design (CAD) models has garnered increasing attention over recent years. Traditional methods often rely on discrete sequences of parametric line/curve segments to represent sketches. Differently, we introduce RECAD, a novel framework that generates Raster sketches and 3D Extrusions for CAD models. Representing sketches as raster images offers several advantages over discrete sequences: 1) it breaks the limitations on the types and numbers of lines/curves, providing enhanced geometric representation capabilities; 2) it enables interpolation within a continuous latent space; and 3) it allows for more intuitive user control over the output. Technically, RECAD employs two diffusion networks: the first network generates extrusion boxes conditioned on the number and types of extrusions, while the second network produces sketch images conditioned on these extrusion boxes. By combining these two networks, RECAD effectively generates sketch-and-extrude CAD models, offering a more robust and intuitive approach to CAD model generation. Experimental results indicate that RECAD achieves strong performance in unconditional generation, while also demonstrating effectiveness in conditional generation and output editing.

Wenhao Zhang, Jun Wang, Yong Luo et al.

Lip-reading is to utilize the visual information of the speaker's lip movements to recognize words and sentences. Existing event-based lip-reading solutions integrate different frame rate branches to learn spatio-temporal features of varying granularities. However, aggregating events into event frames inevitably leads to the loss of fine-grained temporal information within frames. To remedy this drawback, we propose a novel framework termed Multi-view Temporal Granularity aligned Aggregation (MTGA). Specifically, we first present a novel event representation method, namely time-segmented voxel graph list, where the most significant local voxels are temporally connected into a graph list. Then we design a spatio-temporal fusion module based on temporal granularity alignment, where the global spatial features extracted from event frames, together with the local relative spatial and temporal features contained in voxel graph list are effectively aligned and integrated. Finally, we design a temporal aggregation module that incorporates positional encoding, which enables the capture of local absolute spatial and global temporal information. Experiments demonstrate that our method outperforms both the event-based and video-based lip-reading counterparts.

Xuyi Yang, Wenhao Zhang, Hongbo Jin et al.

Current Multimodal Large Language Models (MLLMs) often perform poorly in long video understanding, primarily due to resource limitations that prevent them from processing all video frames and their associated information. Efficiently extracting relevant information becomes a challenging task. Existing frameworks and evaluation tasks focus on identifying specific frames containing core objects from a large number of irrelevant frames, which does not align with the practical needs of real-world applications. To address this issue, we propose a new scenario under the video question-answering task, SceneQA, which emphasizes scene-based detail perception and reasoning abilities. And we develop the LVSQA dataset to support the SceneQA task, which is built upon carefully selected videos from LVBench and contains a new collection of question-answer pairs to promote a more fair evaluation of MLLMs' scene perception abilities in long videos. Inspired by human cognition, we introduce a novel method called SLFG. The core idea of SLFG is to combine individual frames into semantically coherent scene frames. By leveraging scene localization methods and dynamic frame reassembly mechanisms, SLFG significantly enhances the understanding capabilities of existing MLLMs in long videos. SLFG requires no modification to the original model architecture and boasts excellent plug-and-play usability. Experimental results show that this method performs exceptionally well in several long video benchmark tests. Code and dataset will be released at http://www.slfg.pkuzwh.cn.

Pu Li, Wenhao Zhang, Weize Quan et al.

Boundary representation (B-rep) is the de facto standard for CAD model representation in modern industrial design. The intricate coupling between geometric and topological elements in B-rep structures has forced existing generative methods to rely on cascaded multi-stage networks, resulting in error accumulation and computational inefficiency. We present BrepGPT, a single-stage autoregressive framework for B-rep generation. Our key innovation lies in the Voronoi Half-Patch (VHP) representation, which decomposes B-reps into unified local units by assigning geometry to nearest half-edges and sampling their next pointers. Unlike hierarchical representations that require multiple distinct encodings for different structural levels, our VHP representation facilitates unifying geometric attributes and topological relations in a single, coherent format. We further leverage dual VQ-VAEs to encode both vertex topology and Voronoi Half-Patches into vertex-based tokens, achieving a more compact sequential encoding. A decoder-only Transformer is then trained to autoregressively predict these tokens, which are subsequently mapped to vertex-based features and decoded into complete B-rep models. Experiments demonstrate that BrepGPT achieves state-of-the-art performance in unconditional B-rep generation. The framework also exhibits versatility in various applications, including conditional generation from category labels, point clouds, text descriptions, and images, as well as B-rep autocompletion and interpolation.

Gabriel Diaz, Lucky Li, Wenhao Zhang

Reinforcement Learning (RL) has emerged as a powerful framework for sequential decision-making in dynamic environments, particularly when system parameters are unknown. This paper investigates RL-based control for entropy-regularized Linear Quadratic control (LQC) problems with multiplicative noises over an infinite time horizon. First, we adapt the Regularized Policy Gradient (RPG) algorithm to stochastic optimal control settings, proving that despite the non-convexity of the problem, RPG converges globally under conditions of gradient domination and near-smoothness. Second, based on zero-order optimization approach, we introduce a novel model free RL algorithm: Sample-Based Regularized Policy Gradient (SB-RPG). SB-RPG operates without knowledge of system parameters yet still retains strong theoretical guarantees of global convergence. Our model leverages entropy regularization to accelerate convergence and address the exploration versus exploitation trade-off inherent in RL. Numerical simulations validate the theoretical results and demonstrate the efficacy of SB-RPG in unknown-parameters environments.

Wenhao Zhang, Hao Zhu, Delong Wu et al.

Pursuing a continuous visual representation that offers flexible frequency modulation and fast rendering speed has recently garnered increasing attention in the fields of 3D vision and graphics. However, existing representations often rely on frequency guidance or complex neural network decoding, leading to spectrum loss or slow rendering. To address these limitations, we propose WIPES, a universal Wavelet-based vIsual PrimitivES for representing multi-dimensional visual signals. Building on the spatial-frequency localization advantages of wavelets, WIPES effectively captures both the low-frequency "forest" and the high-frequency "trees." Additionally, we develop a wavelet-based differentiable rasterizer to achieve fast visual rendering. Experimental results on various visual tasks, including 2D image representation, 5D static and 6D dynamic novel view synthesis, demonstrate that WIPES, as a visual primitive, offers higher rendering quality and faster inference than INR-based methods, and outperforms Gaussian-based representations in rendering quality.

Kamel Aouaidjia, Aofan Li, Wenhao Zhang et al.

Nowadays, Transformers and Graph Convolutional Networks (GCNs) are the prevailing techniques for 3D human pose estimation. However, Transformer-based methods either ignore the spatial neighborhood relationships between the joints when used for skeleton representations or disregard the local temporal patterns of the local joint movements in skeleton sequence modeling, while GCN-based methods often neglect the need for pose-specific representations. To address these problems, we propose a new method that exploits the graph modeling capability of GCN to represent each skeleton with multiple graphs of different orders, incorporated with a newly introduced Graph Order Attention module that dynamically emphasizes the most representative orders for each joint. The resulting spatial features of the sequence are further processed using a proposed temporal Body Aware Transformer that models the global body feature dependencies in the sequence with awareness of the local inter-skeleton feature dependencies of joints. Given that our 3D pose output aligns with the central 2D pose in the sequence, we improve the self-attention mechanism to be aware of the central pose while diminishing its focus gradually towards the first and the last poses. Extensive experiments on Human3.6m, MPIINF-3DHP, and HumanEva-I datasets demonstrate the effectiveness of the proposed method. Code and models are made available on Github.

Kamel Aouaidjia, Wenhao Zhang, Aofan Li et al.

Existing supervised action segmentation methods depend on the quality of frame-wise classification using attention mechanisms or temporal convolutions to capture temporal dependencies. Even boundary detection-based methods primarily depend on the accuracy of an initial frame-wise classification, which can overlook precise identification of segments and boundaries in case of low-quality prediction. To address this problem, this paper proposes ASESM (Action Segmentation via Explicit Similarity Measurement) to enhance the segmentation accuracy by incorporating explicit similarity evaluation across frames and predictions. Our supervised learning architecture uses frame-level multi-resolution features as input to multiple Transformer encoders. The resulting multiple frame-wise predictions are used for similarity voting to obtain high quality initial prediction. We apply a newly proposed boundary correction algorithm that operates based on feature similarity between consecutive frames to adjust the boundary locations iteratively through the learning process. The corrected prediction is then further refined through multiple stages of temporal convolutions. As post-processing, we optionally apply boundary correction again followed by a segment smoothing method that removes outlier classes within segments using similarity measurement between consecutive predictions. Additionally, we propose a fully unsupervised boundary detection-correction algorithm that identifies segment boundaries based solely on feature similarity without any training. Experiments on 50Salads, GTEA, and Breakfast datasets show the effectiveness of both the supervised and unsupervised algorithms. Code and models are made available on Github.

Yuwei Guo, Wenhao Zhang, Licheng Jiao et al.

Visible-infrared person re-identification (VI-ReID) aims to search the same pedestrian of interest across visible and infrared modalities. Existing models mainly focus on compensating for modality-specific information to reduce modality variation. However, these methods often lead to a higher computational overhead and may introduce interfering information when generating the corresponding images or features. To address this issue, it is critical to leverage pedestrian-attentive features and learn modality-complete and -consistent representation. In this paper, a novel Transferring Modality-Aware Pedestrian Attentive Learning (TMPA) model is proposed, focusing on the pedestrian regions to efficiently compensate for missing modality-specific features. Specifically, we propose a region-based data augmentation module PedMix to enhance pedestrian region coherence by mixing the corresponding regions from different modalities. A lightweight hybrid compensation module, i.e., the Modality Feature Transfer (MFT), is devised to integrate cross attention and convolution networks to fully explore the discriminative modality-complete features with minimal computational overhead. Extensive experiments conducted on the benchmark SYSU-MM01 and RegDB datasets demonstrated the effectiveness of our proposed TMPA model.

Wenhao Zhang, Ramin Ramezani, Arash Naeim

A data science task can be deemed as making sense of the data or testing a hypothesis about it. The conclusions inferred from data can greatly guide us to make informative decisions. Big data has enabled us to carry out countless prediction tasks in conjunction with machine learning, such as identifying high risk patients suffering from a certain disease and taking preventable measures. However, healthcare practitioners are not content with mere predictions - they are also interested in the cause-effect relation between input features and clinical outcomes. Understanding such relations will help doctors treat patients and reduce the risk effectively. Causality is typically identified by randomized controlled trials. Often such trials are not feasible when scientists and researchers turn to observational studies and attempt to draw inferences. However, observational studies may also be affected by selection and/or confounding biases that can result in wrong causal conclusions. In this chapter, we will try to highlight some of the drawbacks that may arise in traditional machine learning and statistical approaches to analyze the observational data, particularly in the healthcare data analytics domain. We will discuss causal inference and ways to discover the cause-effect from observational studies in healthcare domain. Moreover, we will demonstrate the applications of causal inference in tackling some common machine learning issues such as missing data and model transportability. Finally, we will discuss the possibility of integrating reinforcement learning with causality as a way to counter confounding bias.

Ziheng Lin, Yanxiong Li, Zhangjin Huang et al.

Recent efforts have been made on domestic activities classification from audio recordings, especially the works submitted to the challenge of DCASE (Detection and Classification of Acoustic Scenes and Events) since 2018. In contrast, few studies were done on domestic activities clustering, which is a newly emerging problem. Domestic activities clustering from audio recordings aims at merging audio clips which belong to the same class of domestic activity into a single cluster. Domestic activities clustering is an effective way for unsupervised estimation of daily activities performed in home environment. In this study, we propose a method for domestic activities clustering using a convolutional capsule autoencoder network (CCAN). In the method, the deep embeddings are learned by the autoencoder in the CCAN, while the deep embeddings which belong to the same class of domestic activities are merged into a single cluster by a clustering layer in the CCAN. Evaluated on a public dataset adopted in DCASE-2018 Task 5, the results show that the proposed method outperforms state-of-the-art methods in terms of the metrics of clustering accuracy and normalized mutual information.

Dario Fuoli, Zhiwu Huang, Shuhang Gu et al.

This paper reviews the video extreme super-resolution challenge associated with the AIM 2020 workshop at ECCV 2020. Common scaling factors for learned video super-resolution (VSR) do not go beyond factor 4. Missing information can be restored well in this region, especially in HR videos, where the high-frequency content mostly consists of texture details. The task in this challenge is to upscale videos with an extreme factor of 16, which results in more serious degradations that also affect the structural integrity of the videos. A single pixel in the low-resolution (LR) domain corresponds to 256 pixels in the high-resolution (HR) domain. Due to this massive information loss, it is hard to accurately restore the missing information. Track 1 is set up to gauge the state-of-the-art for such a demanding task, where fidelity to the ground truth is measured by PSNR and SSIM. Perceptually higher quality can be achieved in trade-off for fidelity by generating plausible high-frequency content. Track 2 therefore aims at generating visually pleasing results, which are ranked according to human perception, evaluated by a user study. In contrast to single image super-resolution (SISR), VSR can benefit from additional information in the temporal domain. However, this also imposes an additional requirement, as the generated frames need to be consistent along time.

Vishwa Karia, Wenhao Zhang, Arash Naeim et al.

Imbalanced datasets are ubiquitous. Classification performance on imbalanced datasets is generally poor for the minority class as the classifier cannot learn decision boundaries well. However, in sensitive applications like fraud detection, medical diagnosis, and spam identification, it is extremely important to classify the minority instances correctly. In this paper, we present a novel technique based on genetic algorithms, GenSample, for oversampling the minority class in imbalanced datasets. GenSample decides the rate of oversampling a minority example by taking into account the difficulty in learning that example, along with the performance improvement achieved by oversampling it. This technique terminates the oversampling process when the performance of the classifier begins to deteriorate. Consequently, it produces synthetic data only as long as a performance boost is obtained. The algorithm was tested on 9 real-world imbalanced datasets of varying sizes and imbalance ratios. It achieved the highest F-Score on 8 out of 9 datasets, confirming its ability to better handle imbalanced data compared to other existing methodologies.

Wenhao Zhang, Ramin Ramezani, Arash Naeim

Machine learning classifiers often stumble over imbalanced datasets where classes are not equally represented. This inherent bias towards the majority class may result in low accuracy in labeling minority class. Imbalanced learning is prevalent in many real-world applications, such as medical research, network intrusion detection, and fraud detection in credit card transactions, etc. A good number of research works have been reported to tackle this challenging problem. For example, Synthetic Minority Over-sampling TEchnique (SMOTE) and ADAptive SYNthetic sampling approach (ADASYN) use oversampling techniques to balance the skewed datasets. In this paper, we propose a novel method that combines a Weighted Oversampling Technique and ensemble Boosting method (WOTBoost) to improve the classification accuracy of minority data without sacrificing the accuracy of the majority class. WOTBoost adjusts its oversampling strategy at each round of boosting to synthesize more targeted minority data samples. The adjustment is enforced using a weighted distribution. We compare WOTBoost with other four classification models (i.e., decision tree, SMOTE + decision tree, ADASYN + decision tree, SMOTEBoost) extensively on 18 public accessible imbalanced datasets. WOTBoost achieves the best G mean on 6 datasets and highest AUC score on 7 datasets.

Wenhao Zhang, Wentian Bao, Xiao-Yang Liu et al.

Post-click conversion rate (CVR) estimation is a critical task in e-commerce recommender systems. This task is deemed quite challenging under the industrial setting with two major issues: 1) selection bias caused by user self-selection, and 2) data sparsity due to the rare click events. A successful conversion typically has the following sequential events: "exposure -> click -> conversion". Conventional CVR estimators are trained in the click space, but the inference is done in the entire exposure space. They fail to account for the causes of the missing data and treat them as missing at random. Hence, their estimations are highly likely to deviate from the real values by large. In addition, the data sparsity issue can also handicap many industrial CVR estimators which usually have large parameter spaces. In this paper, we propose two principled, efficient and highly effective CVR estimators for industrial CVR estimation, namely, Multi-IPW and Multi-DR. The proposed models approach the CVR estimation from a causal perspective and account for the causes of missing not at random. In addition, our methods are based on the multi-task learning framework and mitigate the data sparsity issue. Extensive experiments on industrial-level datasets show that our methods outperform the state-of-the-art CVR models.

Chunbiao Zhu, Wenhao Zhang, Thomas H. Li et al.

Saliency detection aims to detect the most attractive objects in images and is widely used as a foundation for various applications. In this paper, we propose a novel salient object detection algorithm for RGB-D images using center-dark channel priors. First, we generate an initial saliency map based on a color saliency map and a depth saliency map of a given RGB-D image. Then, we generate a center-dark channel map based on center saliency and dark channel priors. Finally, we fuse the initial saliency map with the center dark channel map to generate the final saliency map. Extensive evaluations over four benchmark datasets demonstrate that our proposed method performs favorably against most of the state-of-the-art approaches. Besides, we further discuss the application of the proposed algorithm in small target detection and demonstrate the universal value of center-dark channel priors in the field of object detection.

Wenhao Zhang, Liangcai Gao, Runtao Liu

Skin cancer, the most common human malignancy, is primarily diagnosed visually by physicians [1]. Classification with an automated method like CNN [2, 3] shows potential for challenging tasks [1]. By now, the deep convolutional neural networks are on par with human dermatologist [1]. This abstract is dedicated on developing a Deep Learning method for ISIC [5] 2017 Skin Lesion Detection Competition hosted at [6] to classify the dermatology pictures, which is aimed at improving the diagnostic accuracy rate and general level of the human health. The challenge falls into three sub-challenges, including Lesion Segmentation, Lesion Dermoscopic Feature Extraction and Lesion Classification. This project only participates in the Lesion Classification part. This algorithm is comprised of three steps: (1) original images preprocessing, (2) modelling the processed images using CNN [2, 3] in Caffe [4] framework, (3) predicting the test images and calculating the scores that represent the likelihood of corresponding classification. The models are built on the source images are using the Caffe [4] framework. The scores in prediction step are obtained by two different models from the source images.