cs.CL（2025-12-15）

📊 共 18 篇论文 | 🔗 1 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (13 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (4) 支柱四：生成式动作 (Generative Motion) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (13 篇)

#题目一句话要点标签🔗⭐
1 Temporal Tokenization Strategies for Event Sequence Modeling with Large Language Models 针对LLM事件序列建模，提出时间Token化策略选择框架，适配不同数据分布。 large language model
2 SkipCat: Rank-Maximized Low-Rank Compression of Large Language Models via Shared Projection and Block Skipping SkipCat：通过共享投影和块跳跃实现大语言模型秩最大化的低秩压缩 large language model
3 Large language models are not about natural language 大型语言模型并非关于自然语言，而是概率模型，对语言学研究无用。 large language model
4 FIN-bench-v2: A Unified and Robust Benchmark Suite for Evaluating Finnish Large Language Models FIN-bench-v2：用于评估芬兰语大型语言模型的统一且鲁棒的基准套件 large language model ✅
5 Efficient Adaptive Rejection Sampling for Accelerating Speculative Decoding in Large Language Models 提出高效自适应拒绝采样(EARS)加速大语言模型推理解码。 large language model
6 MiniLingua: A Small Open-Source LLM for European Languages MiniLingua：一个面向欧洲语言的小型开源LLM，提升指令遵循能力。 large language model instruction following
7 Building from Scratch: A Multi-Agent Framework with Human-in-the-Loop for Multilingual Legal Terminology Mapping 提出一种人机协作的多Agent框架，用于多语种法律术语映射，提升准确性和可扩展性。 large language model
8 Olmo 3 发布Olmo 3：一系列最先进的、完全开源的7B和32B参数规模的语言模型 instruction following
9 Textual Gradients are a Flawed Metaphor for Automatic Prompt Optimization 揭示文本梯度优化Prompt的局限性，挑战其作为优化隐喻的有效性 large language model
10 Fine-tuned LLM-based Code Migration Framework 提出基于微调LLM的代码迁移框架，解决SQL系统迁移难题 large language model
11 Scaling Laws for Code: Every Programming Language Matters 针对代码大语言模型，提出编程语言感知的多语言缩放法则，优化预训练性能。 large language model
12 Uncovering the Role of Initial Saliency in U-Shaped Attention Bias: Scaling Initial Token Weight for Enhanced Long-Text Processing 揭示初始显著性在U型注意力偏差中的作用：通过缩放初始Token权重增强长文本处理 large language model
13 LLM Rationalis? Measuring Bargaining Capabilities of AI Negotiators 提出统一数学框架以量化AI谈判能力 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🔗⭐
14 AutoTool: Dynamic Tool Selection and Integration for Agentic Reasoning AutoTool：面向Agentic推理的动态工具选择与集成框架 reinforcement learning large language model multimodal
15 FiNERweb: Datasets and Artifacts for Scalable Multilingual Named Entity Recognition FiNERweb：构建可扩展的多语命名实体识别数据集及相关工具 teacher-student large language model zero-shot transfer
16 Memory in the Age of AI Agents 对基于大模型Agent的记忆机制进行全面综述，并展望未来发展方向 reinforcement learning foundation model multimodal
17 Nemotron-Cascade: Scaling Cascaded Reinforcement Learning for General-Purpose Reasoning Models 提出级联强化学习Nemotron-Cascade，用于构建通用推理模型。 reinforcement learning RLHF

🔬 支柱四：生成式动作 (Generative Motion) (1 篇)

#题目一句话要点标签🔗⭐
18 ReFusion: A Diffusion Large Language Model with Parallel Autoregressive Decoding ReFusion：一种具有并行自回归解码的扩散大语言模型，提升效率与性能。 MDM large language model

⬅️ 返回 cs.CL 首页 · 🏠 返回主页