HandwritingAgent: Language-Driven Handwriting Synthesis in Scalable Vector Space
Explorar
Noticias de IA
27413 elementos — filtrados, clasificados y sin duplicados
SpectralDiT: Timestep-Conditioned Spectral Residual Correction for Flow-Matching DiTs
SMART: A Flexible, Interpretable, and Scalable Spatio-temporal Brain Atlas from High-Reso…
LegalWorld: A Life-Cycle Interactive Environment for Legal Agents
Trainable Photonic Measurement for Physics-Informed PDE Learning
LLMs Struggle to Measure What Distinguishes Students of Different Proficiency Levels: A S…
UniTemp: Unlocking Video Generation in Any Temporal Order via Bidirectional Distillation
Spatially Stratified Distillation for Heterogeneous Radar Place Recognition
EARS: Explanatory Abstention for Reliable Sub-Agent Modeling in Large-scale Multi-Agent S…
NeuralMUSIC: A Hybrid Neural-Subspace Framework for Robot Sound Source Localization
RegMix-D: Dynamic Data Mixing via Proxy Training Trajectories
LandslideAgent with Multimodal LandslideBench: A Domain-Rule-Augmented Agent for Autonomo…
OmniRetarget: Interaction-Preserving Data Generation for Humanoid Whole-Body Loco-Manipul…
LLM Consumer Behavior Theory: Foundations of a Novel Research Field
Visored: A Controlled-Natural-Language Prover for LLM-Generated Mathematics
LLM-as-Judge in Education: A Curriculum-Grounded Marking Pipeline
Dissecting model behavior through agent trajectories
SP-GCRL: Influence Maximization on Incomplete Social Graphs
CMIP-Forge: An Agentic System that Retrieves, Computes, and Self-Reviews Climate Science
LegalHalluLens: Typed Hallucination Auditing and Calibrated Multi-Agent Debate for Trustw…
Towards Understanding and Measuring COGNITIVE ATROPHY in LLM Behaviour
Can LLMs Be CEOs? Benchmarking Strategic Resource Reallocation with Multi-Role Agent Simu…
High-Fidelity 3D Geometric Reconstruction of Pelvic Organs from MRI: A Hybrid Deep Learni…
S4oP: Operator-level Pruning of Structured State Space Models for Resource-Constrained De…
Looped World Models
Non-negative Elastic Net Decoding for Information Retrieval
RLRC: Reinforcement Learning-based Recovery for Compressed Vision-Language-Action Models
ProvenanceGuard: Source-Aware Factuality Verification for MCP-Based LLM Agents
Explicit Context-Driven Neural Acoustic Modeling for High-Fidelity RIR Generation
PseudoBench: Measuring How Agentic Auto-Research Fuels Pseudoscience