The Price of Hidden Curvature: An $\widetildeΩ (d^{5/4} \sqrt{T})$ Lower Bound for Bandit…
Explorar
Noticias de IA
27413 elementos — filtrados, clasificados y sin duplicados
Fluid-SDF: Ultra-Lightweight and Editable Implicit Shape Representation via Differentiabl…
Mark, Don't Erase: Token Inoculation for Dual-Use Knowledge in LLMs
Graph Neural Network-based Algorithm Selection for the Traveling Salesman Problem: A Syst…
PLAID-PRF: Pseudo-Relevance Feedback with Centroid-like Tokens in PLAID
Norm or Direction? Decoding Vision Mambas for High-Resolution Vision
Stochastic Meta-Unlearning: Bridging Language Backbone and Multimodal Unlearning
Grabette: an open system to record robot-manipulation data
On the Diverse Dynamical Behaviors Arising in Deep Linear Transformers
When Does Machine Learning Beat Value Sorting? A Three-Dataset Diagnostic of Exposure-Wei…
AI just disproved a major math problem. A mathematician explains.
AniGS: Bridging Rendering and Diffusion Prior for 3D Scene Animation
AHEAD: Advancing Multi-Class Label Aggregation with Interpretable Cross-Annotator Modeling
CANDOR: Chance-Calibrated Discordance in Frozen Foundation Encoders
Computational models of pragmatic reasoning with flexible generation of meaning and expre…
Patch Policy: Efficient Embodied Control via Dense Visual Representations
Causal Discovery on Irregular Time Series
Unveiling Invariant and Transferable Latent Factors Across Heterogeneous Environments via…
Three-Body Scattering for Generative Modeling
How Does Alignment Tuning Shape Representations of Sycophancy and Related Cue-Induced Bia…
SciForma: Structure-Faithful Generation of Scientific Diagrams
WorldCupArena: Fine-Grained Evaluation of Language Models and Deep-Research Agents on Foo…
Sparse Evidence Can Suffice: Agentic Evidence Seeking for Multimodal Video Misinformation…
Human Grounded Evaluation of Large Language Models for Optical Network Automation
SAR Vessel Detection and Gross Tonnage Estimation from Heterogeneous Datasets for Dark Ve…
SEE: Structure-aware Exploring \& Exploiting for Long-horizon GUI Agent Trajectory Synthe…
The Shared Discovery Paradox: How a One-Answer Rule Turns Better Information into Worse S…
Adaptive Mamba Neural Operators
Anticipate Before Acting: Future-State-Conditioned Vision-Language Navigation
When 2D Cues Fail: Improving Image Manipulation Localization with Reliable 3D Geometry