cs.CL（2025-12-16）

📊 共 16 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) (16 🔗2)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (16 篇)

#题目一句话要点标签🔗⭐
1 JMMMU-Pro: Image-based Japanese Multi-discipline Multimodal Understanding Benchmark via Vibe Benchmark Construction 提出JMMMU-Pro日语多学科多模态理解基准，并提出Vibe基准构建方法。 multimodal
2 Effect of Document Packing on the Latent Multi-Hop Reasoning Capabilities of Large Language Models 研究文档打包策略对大语言模型多跳推理能力的影响 large language model
3 VLegal-Bench: Cognitively Grounded Benchmark for Vietnamese Legal Reasoning of Large Language Models 提出VLegal-Bench，用于评估LLM在越南法律推理任务中的能力。 large language model
4 SASQ: Static Activation Scaling for Quantization-Aware Training in Large Language Models SASQ：一种面向大语言模型激活量化的静态激活缩放量化感知训练方法 large language model
5 Agreement Between Large Language Models and Human Raters in Essay Scoring: A Research Synthesis 综合研究表明大型语言模型在自动作文评分中与人类评分者具有中等至良好的一致性 large language model
6 Inflation Attitudes of Large Language Models 利用大型语言模型GPT-3.5研究通货膨胀感知与预期，模拟人类调查并分析影响因素。 large language model
7 CogMem: A Cognitive Memory Architecture for Sustained Multi-Turn Reasoning in Large Language Models CogMem：一种认知记忆架构，用于大型语言模型中持续的多轮推理 large language model
8 What Affects the Effective Depth of Large Language Models? 研究揭示大语言模型有效深度受限，为模型优化提供新视角 large language model ✅
9 Ladder Up, Memory Down: Low-Cost Fine-Tuning With Side Nets 提出Ladder Side Tuning以解决大语言模型微调的内存瓶颈问题 large language model chain-of-thought
10 Scalable Frameworks for Real-World Audio-Visual Speech Recognition 提出可扩展框架，提升真实场景下音视频语音识别的鲁棒性。 foundation model multimodal
11 C-ing Clearly: Enhanced Binary Code Explanations using C code C-ing Clearly：利用C代码增强LLM对二进制代码的理解，提升代码解释能力 large language model
12 VersatileFFN: Achieving Parameter Efficiency in LLMs via Adaptive Wide-and-Deep Reuse VersatileFFN：通过自适应宽深复用提升LLM的参数效率 large language model ✅
13 Two CFG Nahuatl for automatic corpora expansion 提出两种CFG Nahuatl方法，用于自动扩展Nawatl语料库 large language model
14 Astraea: A State-Aware Scheduling Engine for LLM-Powered Agents Astraea：面向LLM智能体的状态感知调度引擎，优化端到端延迟 large language model
15 Multilingual and Continuous Backchannel Prediction: A Cross-lingual Study 提出一种多语种连续后通道预测模型，用于研究跨语言的交互时序行为。 zero-shot transfer
16 A Unified Sparse Attention via Multi-Granularity Compression 提出UniSparse以解决长序列自注意力计算瓶颈问题 large language model

⬅️ 返回 cs.CL 首页 · 🏠 返回主页