Why Gated DeltaNet Survives 4-Bit Quantization: NVFP4 W4A4 for the Recurrent Half of a Hy…
Explorar
Noticias de IA
37834 elementos — filtrados, clasificados y sin duplicados
Free Pause Tokens
Seeing Before Synthesizing: VLM-Guided Transition Event Discovery for Weakly-Supervised D…
SHELF: A Synthetic Harness for Multi-Task Bibliographic Benchmarking
More Criticism Does Not Make a Better Review: EquiReview-R
Interface-Induced Trajectory Censoring
Common-Witness Certificates and Sharp Feature Bounds for Counterfactual Image Auditing
Xiaomi-TabLDM: A Tabular Foundation Model Technical Report
STAIR (STructure Aware Information Retriever): A novel dataset and LLM based retriever fo…
Lose the Order, Keep the Hierarchy: Deordering HTN Plans
Towards Numerical TOHTN Planning with SMT-based HTN-SAT Encoding
Speak for Me: Giving LLMs the Situational Awareness to Participate in a Meeting
The Dually Flat Geometry of Planning as Inference
Adapting to Evolving Requirements: Agentic AI for Retail Supply Chain Operations
Bioinfoysis Technical Report
SVG-Score: Human-Aligned Evaluation of Text-to-SVG Generation
CauseCollab: Causal Unified and Modality-Agnostic Network for Heterogeneous Collaborative…
Govern the Model, Not Only the Data: Storage, Circulation, and Learning in Creative AI
Rethinking World Models for Safety-Critical Embodied Systems
DNative-Twin: Decision Graphs and Digital Twins for Reconstructable Agentic Decisions
Analysis of Prompt Engineering for Drug Toxicity Prediction
Counterfactual Routing Using Integer Programming with Constraint Generation
TraveL: Transformer-based Multi-view Path Distributional Representation Learning
KC-Bench: A Dynamic Interactive Benchmark for Evaluating Knowledge Conflicts in LLM Agents
Proactive Service Agents: A Unified Decision Framework, Methods, and Evaluation
GPS-Bench: A Governance Policy Benchmark for Automating Policy Analysis
NeoRed: A Knowledge-Logic-Alignment Multimodal Large Language Model for Neonatal Respirat…
HalluPeer: A Taxonomy-driven Benchmark for Detecting Hallucinations in Scientific Peer Re…
Fresh Memory, Stale Plans: Dependency-Scoped Validation for Distributed LLM-Agent Memory
The Attention Triangle in Audio-Video Models