时间 | 主讲人 | 论文题目 | 附件 | 会议/期刊 |
2026.03.04 | 赖民信 | DTP: A Simple yet Effective Distracting Token Pruning Framework for Vision-Language Action Models | DTP A Simple yet Effective Distracting Token Pruning Framework for Vision-Language Action Models.pptx
| arXiv 2026 |
| 向红静 | Learning to Evict from Key-Value Cache | Learning to Evict from Key-Value Cache.pptx
| ICML 2026 |
2026.03.11 | 李清伟 | Precise memory leak detection for java software using container profiling | Precise memory leak detection for java software using container profiling.pptx
| TOSEM 2013 |
| 杨哲骏 | XY-Serve: End-to-End Versatile Production Serving for Dynamic LLM Workloads | XY-Serve End-to-End Versatile Production Serving for Dynamic LLM.pptx
| ASPLOS 2026 |
2026.03.18 | 魏星迪 | RetroInText: A Multimodal Large Language Model Enhanced Framework for Retrosynthetic Planning via In-Context Representation Learning | RetroInText A Multimodal Large Language Model Enhanced Framework for Retrosynthetic Planning via In-Context Representation Learning.pptx
| ICLR 2025 |
| 孙策 | Speculative Speculative Decoding | Speculative Speculative Decoding.pptx
| ICLR 2026 |
2026.03.25 | 王西霖 | AI-Researcher: Autonomous Scientific Innovation | AI-Researcher Autonomous Scientific Innovation.pptx
| NeurIPS 2025 |
| 周子翔 | Source Code Summarization in the Era of Large Language Models | Source Code Summarization in the Era of Large Language Models.pptx
| ICSE 2025 |
2026.04.01 | 茹祥程 | GoFree: Reducing Garbage Collection via Compiler-Inserted Freeing | GoFree Reducing Garbage Collection via Compiler-Inserted Freeing.pptx
| CGO 2025 |
2026.04.08 | 任明月 | Compiler-R1: Towards Agentic Compiler Auto-tuning with Reinforcement Learning | Compiler-R1 Towards Agentic Compiler Auto-tuning with Reinforcement Learning.pptx
| NIPS 2025 |
2026.04.15 | 王天宸 | REPOAUDIT: An Autonomous LLM-Agent for Repository-Level Code Auditing | REPOAUDIT An Autonomous LLM-Agent for Repository-Level Code Auditing.pptx
| ICML 2025 |
2026.04.29 | 丁伯尧 | Iso Request-Private Garbage Collection | Iso Request-Private Garbage Collection.pptx
| PLDI 2025 |
2026.05.06 | 陈铭瑜 | Toward Scalable Gate-Level Parallelism on Trapped-Ion Processors with Racetrack Electrodes | Toward Scalable Gate-Level Parallelism on Trapped-Ion Processors with Racetrack Electrodes.pptx
| HPCA 2026 |
2026.05.27 | 孙新雨 | CUDA-Agent: Large-Scale Agentic RL for High-Performance CUDA Kernel Generation | CUDA-Agent Large-Scale Agentic RL for High-Performance CUDA Kernel Generation.pptx
| arXiv 2026 |
| 夏金杰 | From what to why: A multi-agent system for evidence-based chemical reaction condition reasoning | From what to why A multi-agent system for evidence-based chemical reaction condition reasoning.pptx
| ICML 2026 |
2026.06.10 | 夏怀琪 | SafeNLIDB: A Privacy-Preserving Safety Alignment Framework for LLM-based Natural Language Database Interfaces | SafeNLIDB A Privacy-Preserving Safety Alignment Framework.pptx
| AAAI 2026 |
| 季扬 | TCCL: Discovering Better Communication Paths for PCIe GPU Clusters | TCCL Discovering Better Communication Paths for PCIe GPU Clusters.pptx
| ASPLOS 2024 |
2026.06.17 | 严盛 | VGGT: Visual Geometry Grounded Transformer | VGGT Visual Geometry Grounded Transformer.pptx
| CVPR 2025 |
2026.06.24 | 刘烁 | OneVL: One-Step Latent Reasoning and Planning with Vision-Language Explanation | OneVL One-Step Latent Reasoning and Planning with Vision-Language Explanation.pptx
| arXiv 2026 |
| 2026.07.08 | 季扬 | FlashOverlap Efficient and Adaptable Overlapping for Computation and Communication via Signaling and Reordering | FlashOverlap :Efficient and Adaptable Overlapping for Computation and Communication .pptx | EuroSys 2026 |
| 2026.07.22 | 丁伯尧 | InspectCoder: Dynamic Analysis-Enabled Self Repair through interactive LLM-Debugger Collaboration | InspectCoder Dynamic Analysis-Enabled Self Repair through interactive LLM-Debugger Collaboration.pptx
| OOPSLA 2026 |
| 陈金宝 | KNighter: Transforming Static Analysis with LLM-Synthesized Checkers | KNighter Transforming Static Analysis with LLM-Synthesized Checkers.pptx
| SOSP 2025 |