cs.CL（2025-12-28）

📊 共 12 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) (2)

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

#题目一句话要点标签🔗⭐
1 Is Chain-of-Thought Really Not Explainability? Chain-of-Thought Can Be Faithful without Hint Verbalization 重新评估思维链解释性：提示词信息缺失不代表不忠实 chain-of-thought
2 LENS: LLM-Enabled Narrative Synthesis for Mental Health by Aligning Multimodal Sensing with Language Models LENS：通过对齐多模态传感与语言模型，实现心理健康的LLM驱动叙事合成 multimodal
3 Forgetting as a Feature: Cognitive Alignment of Large Language Models 提出概率记忆提示，通过模拟人类遗忘机制提升LLM长程推理能力 large language model
4 Harnessing Large Language Models for Biomedical Named Entity Recognition BioSelectTune：一种高效的数据为中心的LLM微调框架，用于生物医学命名实体识别 large language model
5 TabiBERT: A Large-Scale ModernBERT Foundation Model and A Unified Benchmark for Turkish 提出TabiBERT，一个大规模土耳其语ModernBERT基础模型，并构建统一评测基准TabiBench。 foundation model
6 Prompt engineering does not universally improve Large Language Model performance across clinical decision-making tasks 提示工程在临床决策任务中对大语言模型性能的提升并非普适性的 large language model
7 Eliminating Agentic Workflow for Introduction Generation with Parametric Stage Tokens 提出STIG框架，通过参数化阶段令牌消除Agentic工作流，提升LLM生成研究介绍的质量。 large language model
8 Accelerating Language Model Workflows with Prompt Choreography Prompt Choreography：利用动态KV缓存加速LLM工作流 large language model
9 Improving Generalization in LLM Structured Pruning via Function-Aware Neuron Grouping 提出Function-Aware Neuron Grouping (FANG)方法，提升LLM结构化剪枝的泛化能力。 large language model
10 WeDLM: Reconciling Diffusion Language Models with Standard Causal Attention for Fast Inference WeDLM：通过拓扑重排序和因果注意力，加速扩散语言模型的并行推理。 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (2 篇)

#题目一句话要点标签🔗⭐
11 Diversity or Precision? A Deep Dive into Next Token Prediction 提出基于策略梯度的预训练目标，提升LLM在强化学习中的探索能力 reinforcement learning reward shaping large language model
12 AutoForge: Automated Environment Synthesis for Agentic Reinforcement Learning AutoForge：用于Agent强化学习的自动化环境合成方法 reinforcement learning

⬅️ 返回 cs.CL 首页 · 🏠 返回主页