Goose: Anisotropic Speculation Trees for Training-Free Speculative Decoding
Explorar
Noticias de IA
29341 elementos — filtrados, clasificados y sin duplicados
Not All Turns Are Equally Hard: Adaptive Thinking Budgets For Efficient Multi-Turn Reason…
Toward CT-Equivalent Image Quality in Low-Dose Radiotherapy Planning: Conditional Diffusi…
Bounding Hallucinations: Merlin-Arthur Protocols for Mutual-Information Bounds in Languag…
How People Evaluate AI-, Expert-, and Peer-Style Financial Advice
The Belief-Desire-Intention Ontology for modelling mental reality and agency
TGIF: Text-Guided Layer Fusion Mitigates Hallucination in Multimodal LLMs
Multi-Agent AI Safety as an Institutional Design Problem
IndexTTS 2.5 Technical Report
LLM Reasoning for Subjective Tasks: Failure Modes, Mitigation, and Dynamic Reasoning Rout…
When Confidence Fails: Overconfidence in LLMs under Uncertainty and Missing Clinical Info…
LGNNIC: Acceleration of Large-Scale GNN Training using SmartNICs
Artificial Leviathan: Exploring Social Evolution of LLM Agents Through the Lens of Hobbes…
From Inaudible Inputs to Model Failures: Low-Frequency Safety Risks in LALMs
Expert-Guided Multimodal Fusion for Unified Emotion and Sentiment Analysis
LLMs Remember First, Forget Last: Dual-Process Interference in Large Language Models
When LLM Agents Negotiate: Private Information and Dynamic Bargaining in Supply Chains
VCU-Bridge: Hierarchical Visual Connotation Understanding via Semantic Bridging
From Recovery to Drop-off: How Action Post-training Reduces a VLM's Late-Layer Depth Deco…
SARVLM: A Vision Language Foundation Model for Semantic Understanding in SAR Imagery
Length-MAX Tokenizer for Language Models
Reasoning about Intent for Ambiguous Requests
Who Bridges Safety? Identifying and Targeting Cross-Lingual Shared Safety Pathways
Med-CRAFT: An Information System for Explainable and Configurable Construction of Multimo…
RAG-Audio: Retrieval-Augmented Generation for Faithful Brain-to-Audio Reconstruction
SkillClaw: Let Skills Evolve Collectively with Agentic Evolver
Halpern Iteration Achieves $\tilde{\mathcal{O}}(\epsilon^{-1/p})$ $p$th-Order Oracle Comp…
MoNo: Multiscale Optimal Transport Neural Operator for Solving PDEs on General Geometries
Emotion2Skill: Model-Internal Emotion Signals for Adaptive Skill Selection and Evolution
JustLLMGRPO: Radiographic Control for Chest X-Ray Generation