Large Language Models
GPT, Claude, Gemini, and other LLMs
Top This Week
All Content
![[2512.08937] When AI Gives Advice: Evaluating AI and Human Responses to Online Advice-Seeking for Well-Being](https://arxiv.org/static/browse/0.3.4/images/arxiv-logo-fb.png){kind=logo}
Llms
[2512.08937] When AI Gives Advice: Evaluating AI and Human Responses to Online Advice-Seeking for Well-Being
Abstract page for arXiv paper 2512.08937: When AI Gives Advice: Evaluating AI and Human Responses to Online Advice-Seeking for Well-Being
arXiv - AI
·
4 min
·
Llms
[2601.20838] Reward Models Inherit Value Biases from Pretraining
Abstract page for arXiv paper 2601.20838: Reward Models Inherit Value Biases from Pretraining
arXiv - Machine Learning
·
4 min
·
Llms
[2601.20088] Quantization-Aware Distillation for NVFP4 Inference Accuracy Recovery
Abstract page for arXiv paper 2601.20088: Quantization-Aware Distillation for NVFP4 Inference Accuracy Recovery
arXiv - Machine Learning
·
4 min
·
Llms
[2512.03794] AdaptVision: Efficient Vision-Language Models via Adaptive Visual Acquisition
Abstract page for arXiv paper 2512.03794: AdaptVision: Efficient Vision-Language Models via Adaptive Visual Acquisition
arXiv - Machine Learning
·
4 min
·
Llms
[2512.01822] InnoGym: Benchmarking the Innovation Potential of AI Agents
Abstract page for arXiv paper 2512.01822: InnoGym: Benchmarking the Innovation Potential of AI Agents
arXiv - Machine Learning
·
4 min
·
Llms
[2511.21740] A cross-species neural foundation model for end-to-end speech decoding
Abstract page for arXiv paper 2511.21740: A cross-species neural foundation model for end-to-end speech decoding
arXiv - AI
·
4 min
·
Llms
[2511.21722] German General Social Survey Personas: A Survey-Derived Persona Prompt Collection for Population-Aligned LLM Studies
Abstract page for arXiv paper 2511.21722: German General Social Survey Personas: A Survey-Derived Persona Prompt Collection for Populatio...
arXiv - AI
·
4 min
·
Llms
[2601.18753] HalluGuard: Demystifying Data-Driven and Reasoning-Driven Hallucinations in LLMs
Abstract page for arXiv paper 2601.18753: HalluGuard: Demystifying Data-Driven and Reasoning-Driven Hallucinations in LLMs
arXiv - Machine Learning
·
4 min
·
Llms
[2511.10985] When Data is the Algorithm: A Systematic Study and Curation of Preference Optimization Datasets
Abstract page for arXiv paper 2511.10985: When Data is the Algorithm: A Systematic Study and Curation of Preference Optimization Datasets
arXiv - AI
·
4 min
·
Llms
[2601.04786] AgentOCR: Reimagining Agent History via Optical Self-Compression
Abstract page for arXiv paper 2601.04786: AgentOCR: Reimagining Agent History via Optical Self-Compression
arXiv - Machine Learning
·
4 min
·
Llms
[2511.08616] Reasoning on Time-Series for Financial Technical Analysis
Abstract page for arXiv paper 2511.08616: Reasoning on Time-Series for Financial Technical Analysis
arXiv - Machine Learning
·
4 min
·
Llms
[2512.17052] Dynamic Tool Dependency Retrieval for Efficient Function Calling
Abstract page for arXiv paper 2512.17052: Dynamic Tool Dependency Retrieval for Efficient Function Calling
arXiv - Machine Learning
·
4 min
·
Llms
[2512.11582] Brain-Semantoks: Learning Semantic Tokens of Brain Dynamics with a Self-Distilled Foundation Model
Abstract page for arXiv paper 2512.11582: Brain-Semantoks: Learning Semantic Tokens of Brain Dynamics with a Self-Distilled Foundation Model
arXiv - Machine Learning
·
4 min
·
Llms
[2512.04695] TRINITY: An Evolved LLM Coordinator
Abstract page for arXiv paper 2512.04695: TRINITY: An Evolved LLM Coordinator
arXiv - Machine Learning
·
4 min
·
Llms
[2512.03324] Cache What Lasts: Token Retention for Memory-Bounded KV Cache in LLMs
Abstract page for arXiv paper 2512.03324: Cache What Lasts: Token Retention for Memory-Bounded KV Cache in LLMs
arXiv - Machine Learning
·
4 min
·
Llms
[2511.20099] QiMeng-CRUX: Narrowing the Gap between Natural Language and Verilog via Core Refined Understanding eXpression
Abstract page for arXiv paper 2511.20099: QiMeng-CRUX: Narrowing the Gap between Natural Language and Verilog via Core Refined Understand...
arXiv - Machine Learning
·
4 min
·
Llms
[2511.19473] WavefrontDiffusion: Dynamic Decoding Schedule for Improved Reasoning
Abstract page for arXiv paper 2511.19473: WavefrontDiffusion: Dynamic Decoding Schedule for Improved Reasoning
arXiv - Machine Learning
·
4 min
·
Llms
[2510.22210] LSPRAG: LSP-Guided RAG for Language-Agnostic Real-Time Unit Test Generation
Abstract page for arXiv paper 2510.22210: LSPRAG: LSP-Guided RAG for Language-Agnostic Real-Time Unit Test Generation
arXiv - AI
·
4 min
·
Llms
[2510.20487] Steering Evaluation-Aware Language Models to Act Like They Are Deployed
Abstract page for arXiv paper 2510.20487: Steering Evaluation-Aware Language Models to Act Like They Are Deployed
arXiv - AI
·
4 min
·
Llms
[2510.19807] Scaf-GRPO: Scaffolded Group Relative Policy Optimization for Enhancing LLM Reasoning
Abstract page for arXiv paper 2510.19807: Scaf-GRPO: Scaffolded Group Relative Policy Optimization for Enhancing LLM Reasoning
arXiv - Machine Learning
·
4 min
·
Related Topics
Stay updated with AI News
Get the latest news, tools, and insights delivered to your inbox.
Daily or weekly digest • Unsubscribe anytime