cs.CL（2026-07-28）

📊 共 17 篇论文 | 🔗 4 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (12) 支柱二：RL算法与架构 (RL & Architecture) (4 🔗3) 支柱一：机器人控制 (Robot Control) (1 🔗1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (12 篇)

#题目一句话要点标签🔗⭐
1 Evaluating Multi-Turn Multimodal Diagnostic Reasoning on Challenging Real-World Clinical Cases 提出ClinMM-Bench以解决多轮多模态临床诊断评估问题 large language model multimodal
2 MyoCardBench: A Real-World Data Benchmark for Evaluating Large Language Models in Clinically Authentic Cardiovascular Care Scenarios 提出MyoCardBench以解决心血管护理场景下LLM评估问题 large language model multimodal
3 MyMentorLLM: A psychotherapy GenAI environment with multimodal voice/text patients, trainees and experts for deliberate practice 提出MyMentorLLM以解决心理治疗师培训的可扩展性问题 multimodal
4 Construction-Driven Injection: Linguistically-Grounded Edit-Based Code-Mixing Fingerprints for Large Language Models 提出基于语言结构的指纹注入方法以解决现有指纹技术的局限性 large language model
5 Memory for Large Language Models 提出系统化框架以优化大语言模型中的记忆机制 large language model
6 Inspect India Evals: An Open Benchmarking Framework for Evaluating Large Language Models in the Indian Linguistic and Cultural Context 提出Inspect India Evals以解决印度语言模型评估问题 large language model
7 A Human-in-the-Loop Corpus for LLM-Based Simplification of Scientific Summaries 提出人机协作语料库以简化科学摘要 large language model
8 IRIS: Reusable Identity Representations from Frozen LLMs for Entity Alignment 提出IRIS框架以解决知识图谱实体对齐问题 large language model
9 Instruction-Tuned Models Locally Reuse Human Syntax More Than Humans Do 研究表明指令调优模型在语法重用上优于人类 large language model
10 AI's Capability in Assisting Scientific Research in Physics, Astrophysics, and Cosmology II: Project Planning and Proposal Evaluation 探讨大型语言模型在科学项目规划与评估中的应用 large language model
11 AngelSpec: Towards Real-World High Performance Inference with Speculative Decoding 提出AngelSpec以解决大语言模型推理性能问题 large language model
12 AI's Capability in Assisting Scientific Research in Physics, Astrophysics, and Cosmology I: Literature Review 评估大型语言模型在科学文献综述中的辅助能力 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (4 篇)

#题目一句话要点标签🔗⭐
13 TabRank: Chain-of-Thought Distillation for Table Re-Rankers 提出TabRank框架以提升表格重排序性能 distillation chain-of-thought ✅
14 VisualPatchWorld: Code World Models as Latent Structured Representations for Planning 提出VisualPatchWorld以解决世界模型构建的挑战 world model world models ✅
15 Pass the Baton: Trajectory-Relayed On-Policy Distillation 提出Relay-OPD以解决在轨迹蒸馏中的前缀失败问题 teacher-student distillation
16 CAST: Game Solvers as Turn-Level Teachers for LLM Agents 提出CAST以解决长时间游戏中的奖励稀疏问题 reinforcement learning distillation large language model ✅

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
17 Temporal-Distance JEPA: Plan-Aware Representation Learning for Latent World Model Predictive Control 提出TD-JEPA以优化潜在世界模型的预测控制 model predictive control world model world models ✅

⬅️ 返回 cs.CL 首页 · 🏠 返回主页