X-SG$^2$S: Safe and Generalizable Gaussian Splatting with X-dimensional Watermarks
Explorar
Noticias de IA
37834 elementos — filtrados, clasificados y sin duplicados
Ontology-Guided Neuro-Symbolic Inference: Grounding Language Models with Mathematical Dom…
Make Some Noise: Unsupervised Remote Sensing Change Detection Using Latent Space Perturba…
Think Like a Doctor: Conversational Diagnosis through the Exploration of Diagnostic Knowl…
RePro: Proof-Verified Benchmark Rewriting for Reliable Evaluation of LLM Mathematical Pro…
The Rise of Verbal Reinforcement Learning
Designing Proactive Thought Partners for Writing
Adaptive Critical Token-Aware Retrieval for Repository-Level Code Generation
Uncovering the Computational Ingredients of Human-Like Representations in LLMs
Compositional Machine Design as Program Synthesis with LLMs
From Terminology to Diagrams: Visual-Instruction Generation for Scientific Diagram Unders…
Multilingual Medical Reasoning for Question Answering with Large Language Models
KGFR: A Foundation Retriever for Generalized Knowledge Graph Question Answering
Restrict, Don't Retrain: Inference-Time VLM Guidance for Zero-Shot Aerial Segmentation
EEG-VID: Task-Guided Latent Predictive Pretraining for EEG Decoding and Assistive Target …
EM^2Mem: Event-Centric Multimodal Memory for Large Language Models
Good Memory Has ECC: Evaluating the Memory of Vision-Language Models Beyond Accuracy
Verifiable Disaster Storylines and Causal Knowledge Graphs: A Citation-Grounded Pipeline …
A Network Science Perspective on Evaluating Deep Graph Generative Models
Who Judges the Judges? A Chinese Safety QA Benchmark for Evaluating LLM Responses and Saf…
Position Matters: Feature Inversion Attacks in ViT Split Inference with Token Reduction a…
Athena: Vulnerability-Affected Library Identification via Knowledge Graph Completion
REFACTOR-VLA: Unsupervised Library Learning of Typed Motor Programs
Scientific Agent Skills: A Library of Procedural Knowledge for Research Agents
Risk-Aware Decision-Making for Autonomous Overtaking: A World Model-Based Mixture-of-Expe…
Provably Safe Sim-to-Real Transfer
trajectory-judge: What Outcome-Only LLM Judges Miss on Agent Trajectories
H3-World: Turning Language Understanding into World Control
Harness-of-Harness: Multi-Day Autonomous Software Development with Continual Improvement
CHARM: Character Hallucination for Multicultural Role Play Benchmark