NUAAAL

2026-03-09   Inducing Point Operator Transformer: A Flexible and Scalable Architecture for Solving PDEs [slides] 郭泽凯

2026-03-09   Open-set Active Learning 领域研究进展 [slides] 宗辰辰

2026-03-16   SemiReward: A General Reward Model for Semi-supervised Learning [slides] 葛泽庆

2026-03-16   Continuous Exposure-Time Modeling for Realistic Atmospheric Turbulence Synthesis [slides] 曾俊伟

2026-03-23   A-MEM: Agentic Memory for LLM Agents [slides] 王宇

2026-03-23   DATER: Decomposition for Table Reasoning with LLMs [slides] 柴轩轩

2026-03-23   Where MLLMs Attend and What They Rely On: Explaining Autoregressive Token Generation [slides] 彭沛

2026-03-30   FineLIP: Extending CLIP's Reach via Fine-Grained Alignment with Longer Text Inputs [slides] 高星宇

2026-03-30   Why Prompt Design Matters and Works: A Complexity Analysis of Prompt Search Space in LLMs [slides] 杨幸龙

2026-03-30   DomainDrop: Suppressing Domain-Sensitive Channels for Domain Generalization [slides] 张菲倩

2026-04-13   Hallucination Begins Where Saliency Drops [slides] 郝航

2026-04-13   LoRA: Low-Rank Adaptation of Large Language Models [slides] 蒋明忠

2026-04-13   Cut out and Replay: A Simple yet Versatile Strategy for Multi-Label Online Continual Learning [slides] 王子晨

2026-04-13   Discovering Fine-Grained Visual-Concept Relations by Disentangled Optimal Transport Concept Bottleneck Models [slides] 王远见

2026-04-20   Venus: Benchmarking and Empowering Multimodal Large Language Models for Aesthetic Guidance and Cropping [slides] 刘逸凡

2026-04-20   视觉语言导航（VLN）的最新研究进展和代表性工作——DualVLN、OminiNav、JanusVLN、DecoVLN、AgentVLN [slides] 欣子豪

2026-04-27   基于噪声客户端/样本选择的联邦噪声标记学习方法——FedDiv、FedFixer、FedClean [slides] 金彤

2026-04-27   Mixture of Experts Made Personalized: Federated Prompt Learning for Vision-Language Models [slides] 孙佳家

2026-05-11   强化学习与生成式模型结合——Steering Your Diffusion Policy with Latent Space Reinforcement Learning、Flow Q-Learning [slides] 罗钦文

2026-05-11   MDFG: Multi-Dimensional Fine-Grained Modeling for Fatigue Detection [slides] 颜劭铭

2026-05-18   Learning to Select Visual In-Context Demonstrations(LSD) [slides] 葛泽庆

2026-05-18   Enhancing Mixture of Experts with Independent and Collaborative Learning for Long-Tail Visual Recognition [slides] 赵翔鸽

2026-05-25   具身智能体如何实时地自我纠错——World Models、Code-as-Monitor: Constraint-aware Visual Programming for Reactive and Proactive Robotic Failure Detection [slides] 赵东

2026-05-25   Reflected Flows for On-support offline RL via noise Manipulation [slides] 柳溯睿

2026-06-01   Adaptive Action Chunking via Multi-Chunk Q Value Estimation [slides] 陈奕晨

2026-06-01   DiT4SR: Taming Diffusion Transformer for Real-World Image Super-Resolution [slides] 同哲

2026-06-08   On the Resilience of LLM-Based Multi-Agent Collaboration with Faulty Agents [slides] 池昱琦

2026-06-08   Evontree: Ontology Rule-Guided Self-Evolution of Large Language Models [slides] 冷越

2026-06-15   视觉语言导航VLN的最新进展及工作进展——AwareVLN、IDEAL-VLN、MemVLN、InfiniteVLN、AgentVLN [slides] 欣子豪

2026-06-15   Continual Adaptation of Vision Foundational Models for Semantic Segmentation in Adverse Weather [slides] 董夏林

2026-06-22   Attribute-formed Class-specific Concept Space: Endowing Language Bottleneck Model with Better Interpretability and Scalability [slides] 张文良

2026-06-22   From Selective Visual Supervision to Persistent Visual Evidence [slides] 彭沛

2026-06-29   DeepONet as a multi-Operator extrapolation model: Distributed pretraining with physics-informed fine-Tuning [slides] 欧阳瑛子

2026-06-29   R1-VL: Learning to Reason with Multimodal Large Language Models via Step-wise Group Relative Policy Optimization [slides] 杨幸龙

2025-09-01   Aware First, Think Less: Dynamic Boundary Self-Awareness Drives Extreme Reasoning Efficiency in Large Language Models [slides] 文胜涛

2025-09-09   SPARC: Score Prompting and Adaptive Fusion for Zero-Shot Multi-Label Recognition in Vision-Language Models [slides] 葛泽庆

2025-09-09   Bridging RL and Other ML Paradigms [slides] 罗钦文

2025-09-16   Lockdown: Backdoor Defense for Federated Learning with Isolated Subspace Training [slides] 丁宾宾

2025-09-16   CVIT: CONTINUOUS VISION TRANSFORMER FOR OPERATOR LEARNING [slides] 毛佳恒

2025-09-23   AutoSurvey: Large Language Models Can Automatically Write Surveys [slides] 池昱琦

2025-09-23   Qwen VL 系列分享 [slides] 赖彦涛

2025-09-23   Enhancing Few-Shot Class-Incremental Learning via Training-Free Bi-Level Modality Calibration [slides] 李其飞

2025-10-14   Re-thinking Federated Active Learning based on Inter-class Diversity [slides] 宗辰辰

2025-10-21   TAP4LLM: Table Provider on Sampling, Augmenting, and Packing Semi-structured Data for Large Language Model Reasoning [slides] 柴轩轩

2025-10-21   Noise-Resistant Label Reconstruction Feature Selection for Partial Multi-Label Learning [slides] 周傅毅楠

2025-10-28   Reducing Hallucinations in LVLMs [slides] 彭沛

2025-10-28   CLIPood: Generalizing CLIP to Out-of-Distributions [slides] 郑金鹏

2025-11-04   Adaptive Test-Time Personalization for Federated Learning [slides] 卢昕怡

2025-11-04   Distribution-Aligned Decoding for Efficient LLM Task Adaptation [slides] 杨幸龙

2025-11-04   Retinexformer: One-stage Retinex-based Transformer for Low-light Image Enhancement [slides] 张安东

2025-11-11   VAR: VISUAL ATTENTION REASONING VIA STRUCTURED SEARCH AND BACKTRACKING [slides] 郝航

2025-11-11   Call Me When Necessary: LLMs can Efficiently and Faithfully Reason over Structured Environments [slides] 李思威

2025-11-11   CTRLA: ADAPTIVE RETRIEVAL-AUGMENTED GENERATION VIA INHERENT CONTROL [slides] 谭轶

2025-11-18   GSV3D: Gaussian Splatting-based Geometric Distillation with Stable Video Diffusion for Single-Image 3D Object Generation [slides] 温铭浩

2025-11-18   3D-HGS: 3D Half-Gaussian Splatting [slides] 吴盛杰

2025-11-18   VLN发展综述 [slides] 欣子豪

2025-11-25   Chain-of-Thought Prompting for LLMs [slides] 赵东

2025-11-25   Efficient and Long-Tailed Generalization for Pre-trained Vision-Language Model [slides] 赵翔鸽

2025-12-02   LoCoOp: Few-Shot Out-of-Distribution Detection via Prompt Learning [slides] 刘昊哲

2025-12-02   Temporally Consistent Atmospheric Turbulence Mitigation with Neural Representations [slides] 曾俊伟

2025-12-09   Chain of Code: Reasoning with a Language Model Augmented Code Emulator [slides] 吕伟杰

2025-12-16   DAVSP: Safety Alignment for Large Vision-Language Models via Deep Aligned Visual Safety Prompt [slides] 陈浩东

2025-12-16   Driving Fatigue Detection Based on Hybrid Electroencephalography and Eye Tracking [slides] 颜劭铭

2025-12-16   Preference-Based Reinforcement Learning [slides] 周立戎

2025-12-23   Learning with Noisy Labels From A Causal Perspective [slides] 金彤

2025-12-23   PRISM: PROGRESSIVE ROBUST LEARNING FOR OPEN-WORLD CONTINUAL CATEGORY DISCOVERY [slides] 郑腾鑫陵

2025-12-30   Fast Training of Accurate Physics-Informed Neural Networks without Gradient Descent [slides] 李宇

2025-12-30   Principled Fast and Meta Knowledge Learners for Continual Reinforcement Learning [slides] 罗钦文

2026-01-06   MIXING MECHANISMS: HOW LANGUAGE MODELS RETRIEVE BOUND ENTITIES IN-CONTEXT [slides] 赵东

2026-01-06   Scaf-GRPO: Scaffolded Group Relative Policy Optimization for Enhancing LLM Reasoning [slides] 陈俞亦

2026-01-06   rSIM: Incentivizing Reasoning Capabilities of LLMs via Reinforced Strategy Injection [slides] 陆羿

2026-01-13   Scrub It Out! Erasing Sensitive Memorization in Code Language Models via Machine Unlearning [slides] 陈奕晨

2026-01-13   Concentration Distribution Learning from Label Distributions [slides] 刘文俊

2026-01-20   ReSP: Retrieval Summarization with Planning for Multi-Hop Question Answering [slides] 李思威

2026-01-20   TruthX: Alleviating Hallucinations by Editing Large Language Models in Truthful Space [slides] 谭轶

2025-01-06   Composition-Guided Neural Network for Image Cropping Aesthetic Assessment [slides] 刘逸凡

2025-01-06   WHAT MAKES GOOD DATA FOR ALIGNMENT? A COMPREHENSIVE STUDY OF AUTOMATIC DATA SELECTION IN INSTRUCTION TUNING [slides] 吕伟杰

2025-01-06   Multi-Component Graph Convolutional Collaborative Filtering [slides] 吴子涵

2025-01-13   LPFSformer: Location Prior Guided Frequency and Spatial Interactive Learning for Nighttime Flare Removal [slides] 刘睿璇

2025-01-13   Exploring data bias in the VLM model [slides] 彭沛

2025-01-13   Robust Test-Time Adaptation for Zero-Shot Prompt Tuning [slides] 郑腾鑫陵

2025-02-24   Introduction to Real-Time Object Detection [slides] 欣子豪

2025-02-24   Breaking Long-Tailed Learning Bottlenecks: A Controllable Paradigm with Hypernetwork-Generated Diverse Experts [slides] 郑金鹏

2025-03-03   DreamGaussian: Generative Gaussian Splatting for Efficient 3D Content Creation [slides] 吴盛杰

2025-03-03   WHAM: Reconstructing World-grounded Humans with Accurate 3D Motion [slides] 张世杰

2025-03-03   Hyper-opinion Evidential Deep Learning for Out-of-Distribution Detection [slides] 宗辰辰

2025-03-10   Air traffic controllers’ mental fatigue recognition: A multi-sensor information fusion-based deep learning approach [slides] 颜劭铭

2025-03-10   RSHazeDiff: A Unified Fourier-aware Diffusion Model for Remote Sensing Image Dehazing [slides] 曾俊伟

2025-03-10   Fast and Accurate Gigapixel Pathological Image Classification with Hierarchical Distillation Multi-Instance Learning [slides] 周傅毅楠

2025-03-17   Diffusion-based Reinforcement Learning via Q-weighted Variational Policy Optimization [slides] 丁宾宾

2025-03-17   PatchRec: Multi-Grained Patching for Efficient LLM-based Sequential Recommendation [slides] 郭泽凯

2025-03-17   Sa2VA: Marrying SAM2 with LLaVA for Dense Grounded Understanding of Images and Videos [slides] 赖彦涛

2025-03-17   Diffusion-based Reinforcement Learning via Q-weighted Variational Policy Optimization [slides] 周立戎

2025-03-24   Scope: On Detecting Constrained Backdoor Attacks in Federated Learning [slides] 丁宾宾

2025-03-24   Prospective Representation Learning for Non-Exemplar Class-Incremental Learning [slides] 李其飞

2025-03-24   ReZero: Region-Customizable Sound Extraction [slides] 朱新佳

2025-03-31   In Pursuit of Causal Label Correlations for Multi-label Image Recognition [slides] 郝航

2025-03-31   Generate-then-Ground in Retrieval-Augmented Generation for Multi-hop Question Answering [slides] 李思威

2025-03-31   GNOT: A General Neural Operator Transformer for Operator Learning [slides] 毛佳恒

2025-04-07   TIP: Tabular-Image Pre-training for Multimodal Classification with Incomplete Data [slides] 柴轩轩

2025-04-07   Federated Noisy Label Learning [slides] 金彤

2025-04-07   DiffuLT: Diffusion for Long-tail Recognition Without External Knowledge [slides] 赵翔鸽

2025-04-14   LLMEmb: Large Language Model Can Be a Good Embedding Generator for Sequential Recommendation [slides] 牛荣兵

2025-04-14   BGE Landmark Embedding: A Chunking-Free Embedding Method For Retrieval Augmented Long-Context Large Language Models [slides] 谭轶

2025-04-14   Collaborative Large Language Model for Recommender Systems [slides] 王宇

2025-04-14   LightenDiffusion: Unsupervised Low-Light Image Enhancement with Latent-Retinex Diffusion Models [slides] 张安东

2025-04-21   Mining In-distribution Attributes in Outliers for Out-of-distribution Detection [slides] 刘昊哲

2025-04-21   CLIP-Guided Federated Learning on Heterogeneous and Long-Tailed Data [slides] 卢昕怡

2025-04-21   Few-Shot Generative Conversational Query Rewriting [slides] 陶子健

2025-04-28   ABA-FWI: Augmented Boundary Attention for Full Waveform Inversion [slides] 郭泽凯

2025-04-28   Pixel-level and Semantic-level Adjustable Super-resolution: A Dual-LoRA Approach [slides] 温铭浩

2025-04-28   Long-Tailed Out-of-Distribution Detection: Prioritizing Attention to Tail [slides] 赵翔鸽

2025-05-12   Toward Blind Flare Removal Using Knowledge-Driven Flare-Level Estimator [slides] 刘睿璇

2025-05-12   Cropper: Vision-Language Model for Image Cropping through In-Context Learning [slides] 刘逸凡

2025-05-19   Texts as Images in Prompt Tuning for Multi-Label Image Recognition [slides] 熊淑贤

2025-05-19   Open-Vocabulary Calibration for Fine-tuned CLIP [slides] 郑腾鑫陵

2025-05-26   面向高效推理的半监督目标检测方法研究 [slides] 欣子豪

2025-05-26   SynSP: Synergy of Smoothness and Prec