cs.CL（2025-06-16）

📊 共 22 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) (17 🔗2) 支柱二：RL算法与架构 (RL & Architecture) (5)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (17 篇)

#题目一句话要点标签🔗⭐
1 MultiFinBen: Benchmarking Large Language Models for Multilingual and Multimodal Financial Application 提出MultiFinBen以解决多语言多模态金融分析评估问题 large language model multimodal
2 Instruction Following by Boosting Attention of Large Language Models 提出Instruction Attention Boosting以提升大语言模型的指令跟随能力 large language model instruction following
3 From General Reasoning to Domain Expertise: Uncovering the Limits of Generalization in Large Language Models 探讨大语言模型在领域特定推理中的局限性 large language model
4 ROSAQ: Rotation-based Saliency-Aware Weight Quantization for Efficiently Compressing Large Language Models 提出ROSAQ以解决大语言模型量化效率问题 large language model
5 ASMR: Augmenting Life Scenario using Large Generative Models for Robotic Action Reflection 提出一种新框架以增强机器人对用户意图的理解 large language model multimodal
6 An Empirical Study of LLM-as-a-Judge: How Design Choices Impact Evaluation Reliability 研究LLM作为评估者的设计选择对评估可靠性的影响 large language model instruction following
7 Ace-CEFR -- A Dataset for Automated Evaluation of the Linguistic Difficulty of Conversational Texts for LLM Applications 提出Ace-CEFR数据集以解决对话文本语言难度评估问题 large language model
8 Lost in the Mix: Evaluating LLM Understanding of Code-Switched Text 评估大型语言模型对代码切换文本的理解能力 large language model
9 Investigating the interaction of linguistic and mathematical reasoning in language models using multilingual number puzzles 探讨语言模型中语言与数学推理的交互以解决数字难题 large language model
10 Steering LLM Thinking with Budget Guidance 提出预算引导方法以优化大语言模型的推理效率 large language model ✅
11 Prefix-Tuning+: Modernizing Prefix-Tuning by Decoupling the Prefix from Attention 提出Prefix-Tuning+以解决传统Prefix-Tuning在LLMs中的局限性 large language model
12 EvolvTrip: Enhancing Literary Character Understanding with Temporal Theory-of-Mind Graphs 提出EvolvTrip以增强文学角色理解能力 large language model ✅
13 Mixture of Weight-shared Heterogeneous Group Attention Experts for Dynamic Token-wise KV Optimization 提出mixSGA以解决Transformer模型动态KV优化问题 instruction following
14 TensorSLM: Energy-efficient Embedding Compression of Sub-billion Parameter Language Models on Low-end Devices 提出TensorSLM以解决低端设备上语言模型能效问题 large language model
15 Position: Pause Recycling LoRAs and Prioritize Mechanisms to Uncover Limits and Effectiveness 提出重用LoRAs的有效性分析以解决模型整合问题 large language model
16 Abstract, Align, Predict: Zero-Shot Stance Detection via Cognitive Inductive Reasoning 提出Cognitive Inductive Reasoning框架以解决零样本立场检测问题 large language model
17 Unveiling the Learning Mind of Language Models: A Cognitive Framework and Empirical Study 提出认知框架以揭示语言模型的学习能力 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🔗⭐
18 VL-GenRM: Enhancing Vision-Language Verification via Vision Experts and Iterative Training 提出VL-GenRM以解决视觉语言模型训练中的偏差问题 reinforcement learning large language model multimodal
19 CAMS: A CityGPT-Powered Agentic Framework for Urban Human Mobility Simulation 提出CAMS框架以解决城市人类移动模拟中的数据驱动不足问题 DPO large language model foundation model
20 BOW: Reinforcement Learning for Bottlenecked Next Word Prediction 提出BOW方法以解决语言模型推理能力不足的问题 reinforcement learning large language model
21 Language Agents for Hypothesis-driven Clinical Decision Making with Reinforcement Learning 提出基于假设驱动的语言代理以提升临床决策支持 reinforcement learning large language model
22 Alignment Quality Index (AQI) : Beyond Refusals: AQI as an Intrinsic Alignment Diagnostic via Latent Geometry, Cluster Divergence, and Layer wise Pooled Representations 提出AQI以解决大型语言模型对齐评估问题 RLHF DPO large language model

⬅️ 返回 cs.CL 首页 · 🏠 返回主页