cs.CL（2026-10-07）

📊 共 25 篇论文 | 🔗 2 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (19 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (5 🔗1) 支柱一：机器人控制 (Robot Control) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (19 篇)

#	题目	一句话要点	标签	🔗	⭐
1	SpikingVLA: Asynchronous Spiking Vision-Language-Action Models	提出SpikingVLA以解决低延迟脉冲视觉语言行动模型问题	vision-language-action VLA
2	Document-Level Text Simplification in Estonian Using Large Language Models	提出文档级文本简化方法以解决爱沙尼亚语低资源问题	large language model
3	InterView-C: A Synchronized Multimodal Corpus of VR Avatar-Mediated Survey Interviews	提出InterView-C以解决虚拟现实中多模态访谈数据不足问题	multimodal
4	The Long Road to the Same Answer: Cognitive Bias Under Escalating Reasoning Budgets in Large Language Models	探讨大型语言模型推理预算对认知偏见的影响	large language model
5	RELATE: An Evaluation Framework for measuring Relational Orientation of Large Language Models	提出RELATE框架以评估大型语言模型的关系导向	large language model
6	Certified by Abstention: Distribution-Free Guarantees for Chain-of-Thought Verifiers at Small Calibration Budgets	提出基于弃权的认证方法以解决小规模标定预算下的链式思维验证问题	chain-of-thought
7	EngramEdit: Decoupled Knowledge Updates in LLMs through Conditional Memory	提出EngramEdit以实现大语言模型的知识独立更新	large language model chain-of-thought
8	PHRBench: A Behavioral Evaluation of Post-Hallucination Reasoning in LLMs	提出PHRBench以评估大语言模型的后幻觉推理行为	large language model
9	A Deafening Silence: Catastrophic Forgetting Lives in the Output Embeddings of Tokens the Data Never Speaks	提出一种优化方法以减少大语言模型中的灾难性遗忘问题	large language model
10	From Pareto to Preference: Personalized Test-Time Scaling via Amortized Agentic Policy Discovery	提出PersonTTS以解决个性化测试时间缩放问题	large language model
11	How Do LLMs Change Predictions Under Negation?	提出新训练目标以改善大语言模型的否定处理能力	large language model
12	Arctic Questions, Missing Answers: A Dataset and Benchmark for LLM Abstention in Arctic Science	提出ArcticQA数据集以解决LLM在北极科学中的回答缺失问题	large language model	✅
13	HySPE: Positional Encoding via Symplectic Dual Shears	提出HySPE以解决位置编码的数值稳定性问题	foundation model
14	EASE: Entropy-Adaptive Distribution Shaping for Evading AI-generated Text Detectors	提出EASE以规避AI生成文本检测器的挑战	large language model
15	Shaer: Controlled Arabic Poetry Generation with Meter Subform and Semantic Conditioning	提出Shaer框架以解决阿拉伯诗歌生成的多重约束问题	foundation model
16	Towards Explaining Query Expansion Performance in Information Retrieval	提出理想扩展查询模型以解释信息检索中的查询扩展性能	large language model
17	InsClaimBench: Benchmarking Insurance Claim Adjudication Across the Decision Chain	提出InsClaimBench以评估保险索赔裁决过程中的决策链	large language model
18	Rubric Spans are Label Representations: Joint LLM Encoding for Short Answer Scoring	提出RUSPAN框架以提升短答案评分的准确性与效率	zero-shot transfer
19	Goldsmith: Gold-Loss-Guided Definition Optimization with an Agentic Annotation Harness	提出Goldsmith以解决稀缺专家监督下的注释定义优化问题	large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (5 篇)

#	题目	一句话要点	标签	🔗	⭐
20	OnlineQAT: On-Policy Distillation for Ultra-Low-Bit Large Language Models	提出OnlineQAT以解决低比特量化模型的准确性恢复问题	distillation large language model
21	SAPD: Step-Aligned Privileged Distillation	提出SAPD方法以解决大语言模型的高成本后训练问题	reinforcement learning policy learning distillation	✅
22	Beyond Outcome Rewards: Constructing and Assigning Retrieval Credit for Search Agents	提出中间监督机制以提升搜索代理的强化学习效率	reinforcement learning reward design reward shaping
23	Mechanics of Long-Context Hybrid Models Part 1.1: From Hybrid Attention to Hybrid Position	提出混合注意力模型以提升长上下文处理效率	linear attention large language model
24	On-Policy Distillation Teaches New Skills but Not New Knowledge	提出在政策蒸馏方法以提升推理能力但不增加知识	distillation

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
25	LLM Persuasion Is in the Eye of the Evaluation	提出统一评估框架以解决LLM说服力评估不一致问题	manipulation large language model

⬅️ 返回 cs.CL 首页 · 🏠 返回主页