Tracking the Behavioral Trajectories of Adapting Agents
Explorar
Noticias de IA
21813 elementos — filtrados, clasificados y sin duplicados
Drifting Preference Optimization for One-Step Generative Models
GloResNet: A lightweight 3D CNN with global topological features for preterm brain injury…
Expressivity of congruence-based architectures for DNNs on positive-definite matrices
AI Agent Guidelines for CS336 at Stanford
Learning When to Translate for Multilingual Reasoning
Active Exploring like a Pigeon: Reinforcing Spatial Reasoning via Agentic Vision-Language…
Spectral Audit of In-Context Operator Networks
Evolutionary Discovery of Bivariate Bicycle Codes with LLM-Guided Search
Honey, I Shrunk the Arc de Triomphe!
TROPHIES: Temporal Reconstruction of Places, Humans, and Cameras from Multi-view Videos
Beyond Isolated Behaviors: Hierarchical User Modeling for LLM Personalization
Towards Resolving Optimization Conflicts Between Image- and Text-Based Person Re-Identifi…
The Ghost Couple: Correlated LLM Name Priors and Their Haunting of the Web and Academic P…
Edge-aware Decoding for Neural Asymmetric Routing
ProbRes: Volatility Learning for Probabilistic Time-Series Forecasting
Error Bounds for a Diffusion Model-Based Drift Estimator
LALE: Lightweight-Transformer Architecture for Land-Cover Estimation
An OpenAI model solved a famous math problem that stumped humans for 80 years
Realistic noise synthesis reduces bias and improves tissue microstructure estimation with…
SentGuard: Sentence-Level Streaming Guardrails for Large Language Models
OpenWebRL: Demystifying Online Multi-turn Reinforcement Learning for Visual Web Agents
World-Task Factorization for Robot Learning
Extreme Low-Bit Inference in Reasoning Models: Failure Modes and Targeted Recovery
Provable Data Scaling Law for Meta Learning via Complexity Minimization
CARTE: A Benchmark for Mapping Language Model Knowledge Across France
MT-EditFlow: Reinforcement Learning for Multi-Turn Image Editing with Flow Matching
WALL-WM: Carving World Action Modeling at the Event Joints
Beyond Low-Rank: Low-Rank Sparse Prompting via Spiking Neural Network and Prompt Factoriz…
The Lie We Tell: Correcting the Euclidean Fallacy in Vision Language Action Policies via …