What do Reward Models Memorize?
Explorar
Noticias de IA
27413 elementos — filtrados, clasificados y sin duplicados
Evaluating RAG for French immigration law: a benchmark and baseline study
DraftExpert: Expansion-Aware Self-Speculative Decoding for End-Device MoE Inference
InterOCF: Spatio-Temporal 2D-3D Interaction for Camera-Only 4D Occupancy Forecasting
Context Is King: How In-Context Specification Shapes the Geometry of Concepts
MAViE: A Multi-scale Adaptive Vision Encoder for Fine-grained Visual Perception and Effic…
GenSplatCodec: Feed-Forward Gaussian Splatting Compression via One-Step Diffusion
Multivariate Time Series Forecasting with Adaptive Non-Local Observables
Beyond Aggregate Risk: Role-Stratified Conformal Risk Control for LLM Tool Calls
CONSISTRE: A Unified Consistency-Aware Framework for Document-Level Relation Extraction w…
Rethinking the Generation Order of Block Diffusion Language Models
Teacher Knows It Best: Spontaneous Symmetry Breaking and Tipping Points in Networked Lang…
Multiview Multi-Person Human Mesh Recovery Under Large Scenes with Occlusions
UMI3D: Robust 3D Generation on Unconstrained Multi-Image Inputs via Simultaneous Focus Cr…
Closing the data loop in AI-driven drug discovery
The Tokenizer Tax: Quantifying and Explaining the Cross-Lingual Cost of Subword Tokenizat…
Catalyst Diffusion Transformer: Generative Inverse Design of Heterogeneous Catalysts
SILICA: Repurposing Diffusion Priors for Joint Glass Segmentation and Depth Estimation
FilmBench: A Film-Grade Benchmark for Cinematic Video Generation
How AI is shortening drug discovery timelines in China
MATS: A novel multi-modality multi-task learning framework for 3D perception in autonomou…
Effect of User-Prompted Priors on Semi-Automated Cancer Lesion Segmentation in Whole-Body…
LCMamNet: A Lightweight Cross-scale Mamba Network for Infrared Small Target Detection
Where Quality Breaks in Compressed Short-Text Generation: Staged Bottleneck Localization
Agent-UCT: Upper Confidence Bounds Applied to Trees for Agentic Workflow Optimization wit…
Calibrated Tree-Neural Fusion for Fine-Grained Vegetation Community Classification
DeVA: Decoupled Video-Action Model with physical guidance for robot policy learning
UniGen-AR: Unifying Visual Generation with Auto-Regressive Modeling
A Motion-Aware Vector Quantization Framework with Centroid Reuse for Efficient VLA Infere…
TEmBed-T: A Multi-Dimensional Benchmark for Table-Level Embeddings