Vibe Patenting: Evaluating LLM Judges for Professional Patent-Drafting Agents
Explorar
Noticias de IA
27413 elementos — filtrados, clasificados y sin duplicados
Toward Self-Adaptive Physical AI: Can LLM Agents Manage Long-Horizon Physical Tasks?
Root-Cause Attribution Is a Search Problem: Continual Search for Long-Horizon Agent Failu…
Fraglingo: Molecular Design via Attachment-Aware Autoregressive Fragment Generation
Hallucination in Multimodal Foundation Models: A Survey on Causes, Corrections, and Evalu…
Privileged observations enable rapid and reliable policy discovery directly in the physic…
Causal multi-modal AI for personalized chemosensitivity prediction
How User-AI Mistreatment Occurs and Matters in Conversational Systems?
How Lossless Is Lossless Speculative Decoding? The Role of Numerical Precision in Orthrus
Privacy-enhanced federated learning via asynchronous aggregation and local differential p…
The Router Within: Eliciting Native Skill Routing from a Frozen LLM
GeoSkill:Experience-Driven Hierarchical Skill Learning with Collaborative Revision forGeo…
FICAug: Feature-Informed Clustering and Augmentation for Facial-Expression-Based Parkinso…
Partition Scores Are Not System Scores: Deployment-Fidelity Gaps in Decomposed Algorithm …
Bypass Observation: A Conceptual Design of a Non-Intrusive Layer-Wise Semantic Extraction…
ViperQ: Order Flow Pattern Recognition via Auction Market Theory for Reinforcement Learni…
LoRA Fine-Tuned Models for Control Systems Course Q\&A: A Multidimensional Evaluation of …
Synthetic Data in Marketing Research: How to Evaluate and When to Trust
Semantic Knowledge Technologies: what the Semantic Web lost sight of, and what it never h…
Schizophrenia Detection from EEG Signals: A Transformer Framework with Spectrogram Repres…
ClinicalReTrial: Clinical Trial Redesign with Self-Evolving Agents
Towards a Mechanistic Understanding of Propositional Logical Reasoning in Large Language …
OptoAgent: A Trustworthy Multi-Agent Framework for Opportunistic Vision Micro-Screening i…
Refinement-based Flow Policy Optimization
mKernel: Fast Multi-GPU, Multi-Node Fused Kernels
MCPAgentBench: A Real-world Task Benchmark for Evaluating LLM Agent MCP Tool Use
Echo-CoPilot: A Multiple-Perspective Agentic Framework for Reliable Echocardiography Inte…
CodeTS: Verifiable Text-to-Time Series Generation via Executable Code
DiTAR+: Dual Optimization for Robust Autoregressive Diffusion Speech Synthesis
CRAMER: Control via Request-Aware Masking for Editing Recommenders