首页 > 专栏 > cs.CL updates on arXiv.org cs.CL updates on arXiv.org 共 5072 条资讯 Learning a Vector-Symbolic Model for Socio-Cultural Tasks 2026-06-28 03:07:22 ACE-GraphRAG: Agentic Context Engineering for Hierarchical GraphRAG 2026-06-28 03:07:22 Do VLMs Align Better with Humans than LLMs during Natural Reading? 2026-06-28 03:07:22 Crayotter: Learning Long-Horizon Video Editing Agents via Group-Relative Preference Backpropagation 2026-06-28 03:07:22 Self-Guided Adaptive Safety Alignment: Synthesizing and Internalizing Guidelines in Reasoning Models 2026-06-28 03:07:22 Stuck on "A": Diagnosing and Repairing Interface Injury in Attention-to-KDA Linearization of a 0.6B Language Model 2026-06-28 03:07:22 ParVL: Parallel Scaling and Expandable Compute Allocation for Multimodal LLMs 2026-06-28 03:07:22 MemArena: An Ego-Centric Benchmark for On-Device Agentic Personal Memory Assistants at Scale 2026-06-28 03:07:22 OncoTriad-QA: A Patient-Level Radiology-Pathology-Genomics Benchmark for Pan-Cancer Reasoning 2026-06-28 03:07:22 Evaluating OpenAI's Privacy Filter: Cross-Lingual, Cross-Domain PII Detection Across 42 Benchmarks 2026-06-28 03:07:22 JudgeArena: A Unified Framework for Reproducible LLM-Judge Evaluation 2026-06-28 03:07:22 Preferred, Not Safer: Pairwise Preference Is a Poor Proxy for Clinical Safety 2026-06-28 03:07:22 Speculative Correction: Draft-then-Refine Decoding for Diffusion Language Models 2026-06-28 03:07:22 Knowing the Form, Not the Function: Automatically Auditing Answer--Authority Decoupling in Legal Benchmarks 2026-06-28 03:07:22 Pingala: Prosody-Aware Decoding for Sanskrit Poetry Generation 2026-06-28 03:07:22 Mechanism of Task-oriented Information Removal in In-context Learning 2026-06-28 03:07:22 The Tell-Tale Trace: Detecting Reasoning Failures in LLMs Using Chain-of-Thought Dynamics 2026-06-28 03:07:22 Convex-Hull-Neighborhood Smooth Dual Generalization: Controlling Local Correction Propagation in Offline RL 2026-06-28 03:07:22 When Outputs Disperse, Does Epistemic Revision Follow? A Black-Box Coupling Diagnostic for Machine Collectives 2026-06-28 03:07:22 ARCHead: Activation-Metric Residual Correction for Large Language Model Output Heads 2026-06-28 03:07:22 « 上一页1…156157158159160…254下一页 » 相关分类 #!/slash/note #UNTAG (B)(F)uzzing on my world (Hi)story (IN)SECURE Magazine Notification (gdb) break *0x972 - 带鱼博客 BeltfishBlog - ./kwaa.dev .NET Blog .Trash /home/rook1e 00's Adventure 0kami's Blog 0x41414141 in ?? () 0x7f Blog 0xRick Owned Root ! 0xd00's blog 1 Byte 1A23 Blog 1A23 Studio 1Link.Fun 1stwebdesigner 251 2BAB 的工程博客 2ch中文网 360 CERT 360 Netlab Blog - Network Securi 38号车评中心 3o米的微博 404 Media