LOCI: A Locator-Critic with Refinement Loop
Explorar
Noticias de IA
37834 elementos — filtrados, clasificados y sin duplicados
CoMPASS: Collaborative Molecular Property Prediction via Adaptive Small-Large Model Syner…
Fine-Grained Multi Image Object Hallucination Benchmark
Cost-efficient Active Learning for Referring Image Segmentation and Grounding
BiG-SURE - Bipartite Graph for Semantic Uncertainty and Reliability Estimation of LLMs
Reading the News: Adapting Large Language Models to Swedish Journalism Through Continued …
Beyond Correctness: Validity-Oriented Evaluation of Biomedical LLM Judges
Game-Agnostic Value Functions through Automatic JSON Feature Extraction
MI-Distillation: Selecting from Model-Interpolated Instruct-Reasoning Data Spectrum for C…
Tensor Methods for Language Models: From Token Representation to Training, Adaptation, In…
Lot Machine: Multimodal Lot Extraction from Auction Catalogs
Trajectory-Initialized Neural Double Q-Routing for Large-Scale Overhead Hoist Transport S…
Preference Shapes Relevance: Cross-component Hierarchical Semantic Alignment for Personal…
Flow-JEPA: Flow Matching for Robust Latent Dynamics in JEPA World Models
Lies We Can See: Joint Verbal and Non-Verbal Deception by VLM Agents in Embodied Social I…
CoJEPA: Combining Contrastive Learning and JEPA for Global-Local Music Representations
Enhancing Low-Resource Language Reasoning via High-Resource Language Feature Transfer
Whole-Slide Image Analysis under Realistic Few-Shot Annotation Protocols
Collapsibility of Performance Metrics in Clinical Predictive AI
SePArate: Segmenting Patterns from Defects in Wafer Manufacturing Using Weak Supervision
Measuring Memory and Generalization as Separable Geometric Channels: The Topo^2 Framework
Using Grounded Theory for Agent Behavior Analysis at Scale
TopGQ: Fast GNN Post-Training Quantization Leveraging Topology Information
AutoScientist-Quant: Self-Evolving Coding Agents for Automatic Research in Quantitative I…
DiffSAC: Diffusion-guided Sampling for Consensus-based Robust Estimation
ImageCAS-X: a dataset and benchmark for coronary artery segmentation and centerline extra…
PAVE: Predictive Alignment and Value-Guided Evolution for World-Action Policies
Beyond Ranking Accuracy: Evaluating LLM-Cited Feature Rationales for Next Basket Repurcha…
DASC: Decay-Aware State Compression for Hybrid Linear-Attention Serving
Beyond Token-Level Guidance: Inference-Time Alignment of Specialized LLMs via Cross-Famil…