cs.CL（2026-01-22）

📊 共 11 篇论文

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (10) 支柱二：RL算法与架构 (RL & Architecture) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (10 篇)

#	题目	一句话要点	标签	🔗	⭐
1	Stable-DiffCoder: Pushing the Frontier of Code Diffusion Large Language Model	Stable-DiffCoder：通过块扩散持续预训练，提升代码生成大语言模型性能。	large language model
2	ExDR: Explanation-driven Dynamic Retrieval Enhancement for Multimodal Fake News Detection	提出ExDR框架，通过解释驱动的动态检索增强，提升多模态假新闻检测性能。	multimodal
3	Towards Reliable Medical LLMs: Benchmarking and Enhancing Confidence Estimation of Large Language Models in Medical Consultation	提出MedConf框架，提升医学LLM在多轮诊疗中置信度评估的可靠性	large language model
4	YuFeng-XGuard: A Reasoning-Centric, Interpretable, and Flexible Guardrail Model for Large Language Models	提出YuFeng-XGuard，一个以推理为中心、可解释且灵活的LLM安全防护模型。	large language model
5	Evaluating and Achieving Controllable Code Completion in Code LLM	提出C3-Bench基准测试，并利用数据合成与微调提升代码大模型指令可控的代码补全能力。	large language model instruction following
6	HumanLLM: Towards Personalized Understanding and Simulation of Human Nature	HumanLLM：构建个性化人类行为理解与模拟的基座模型	large language model foundation model
7	ToxiTwitch: Toward Emote-Aware Hybrid Moderation for Live Streaming Platforms	ToxiTwitch：面向直播平台的表情符号感知混合型恶意内容检测	large language model multimodal
8	Improving Training Efficiency and Reducing Maintenance Costs via Language Specific Model Merging	提出语言特定模型合并方法，提升多语言LLM训练效率并降低维护成本。	large language model
9	Adapter Fusion for Multilingual Text2Cypher with Linear and Learned Gating	提出基于Adapter Fusion的线性与可学习门控方法，提升多语言Text2Cypher性能。	large language model
10	Beyond Marginal Distributions: A Framework to Evaluate the Representativeness of Demographic-Aligned LLMs	提出评估框架，通过多元相关性分析提升人口统计对齐LLM的代表性。	large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
11	LLM-in-Sandbox Elicits General Agentic Intelligence	LLM-in-Sandbox：利用代码沙箱激发LLM在非代码领域的通用智能	reinforcement learning instruction following

⬅️ 返回 cs.CL 首页 · 🏠 返回主页