From Visual Feedback to Textual Reviews: A Multi-Agent Vision-Language Framework for Imag…
Explorar
Noticias de IA
27413 elementos — filtrados, clasificados y sin duplicados
MulRobBench: A Decision-Level Benchmark for Safe and Security-Policy-Compliant Multimodal…
Interpretable Inverse Design of Metal-Organic Frameworks with Large Language Model Agents
Dissociating performance from compositional feature learning
Refusal Reads Only a Slice of What the Model Knows: Harm-Keyed Routing and Its Exceptions…
Calibrating Interpretability Instruments Before Trusting Their Verdicts
A Few Pages of Markdown: Committed AI Configuration and Lower Quality Cost after Coding-A…
Looping Is Not Reliability: State-Bound Evidence and Typed Revision Contracts for Agentic…
Mind Which Bird You Favour: Parameterizing Adequacy-Fluency Balance in Meta-Evaluation of…
LIMBO: Lifelong Inference-Time Memory and Budget Optimization for LLM Agents
Neural-Network Solutions to Real-Space Charge Density and Generalization
LPA-CWM: A Learned Physical Adjudicator for Motion Reasoning with Counterfactual World Mo…
The Stochastic Deputy: Structural Tenant Isolation for Tool-Using LLM Agents
Towards Evolving Context Parameterization for Large Language Models
Loop-Back Authority in LLM Agent Teams: A Paired Experiment on Flat and Hierarchical Coor…
Same Patient, Different Order: Action-Level Reliability of Clinical LLM Agents Under Repe…
RAIN: Region-Aware Inversion Network for Semantic Watermark Extraction
Forty Shades of Blue: Quality-Diversity Alignment via Mode-Conditioned Reinforcement Lear…
Route, Don't Fix: Regime-Dependent Decoding Correction and a Trajectory-Gated Router for …
AI Psychosis: Does Conversational AI Amplify Delusion-Related Language?
Semantic Fibers and Cross-Gram Interference: A Calculus of Safety Drift in Overcomplete R…
SeqMaestro: From nucleotide sequences to biological hypotheses through interpretable mach…
Useless but Safe? Benchmarking Utility Recovery with User Intent Clarification in Multi-T…
Putting HUMANS first: Efficient LAM Evaluation with Human Preference Alignment
Validating Hybrid-State Cache Recovery for GLM-5.3-Flash with vLLM and LMCache
Legislating World-Model-Based Planning with Legal Reasoning
Rethinking Procedural Audio Pre-training: Source Scaling and Objective Adaptation
Canaries in the Bank: Auditing User-Level Privacy in Private Evolution
LiftGCN: Efficient Energy-Preserving Graph Learning via Joukowski Spectral Lifting for Fi…
MAPS: Memory-Aware Predictive Scheduling Framework for Large Language Model Serving