From local kernels to global form: modeling the emergence of musical content
Explorar
Noticias de IA
27413 elementos — filtrados, clasificados y sin duplicados
On-Policy Self-Distillation in Diffusion Models
IAPO: Influence-Aware Policy Optimization for Credit Assignment in Multi-Turn Service Age…
X-MULTI: VLM-based Imaging Factor Disentanglement for Factor-Aware Image Synthesis
From Numerical Simulators of PDEs to Neural Emulators and Back
Hierarchical Prototype-Memory Adaptation of SAM for Surgical Instrument Segmentation
It depends: Incorporating correlations for joint aleatoric and epistemic uncertainties of…
SatDL: Jointly Optimizing Data Redistribution and Training for Satellite-Based Distribute…
Beyond Static Interpretability: Anticipating Post-SFT Mechanisms from Pre-SFT Parameters …
HMGCLIP: Heterogeneous Multi-Granularity Contrastive Learning for E-commerce Representati…
DoublesEval: Diagnosing Multi-Agent Tactical Reasoning in Vision-Language Models via Prof…
Quantization-Aware Healing: a compressed, 4-bit model that outperforms its full-precision…
Markerless Pose Estimation for Resistance Training Technique Assessment
MaST: Motion-aware Sparse Pipeline for Lightweight Object Tracking
Mind the Student: Behavioral and Contextual Cues for Automated Engagement Prediction in O…
OPDSearch+: On-Policy Distillation with RL Refinement for Search-Augmented Reasoning
RePolicy: Reinforcement Learning for Safety-Policy Invocation in Agent Safeguards
RecurSE: Bounded Recursive Self-Evaluation for LLM Rubric Judges
A Data-dependent Early Stopping Rule using Rademacher Complexity with L1-norm
PRQ-KMeans: Projection Residual Quantization for Semantic ID Tokenization
Preference Data Selection for Mitigating the Alignment Tax in Large Language Models
Paritok-4B: Intent-Conditioned Context Compression for Coding Agents
Robust Data-Collection Policy Learning for Low-Variance Online Policy Evaluation
A mesh-free multiresolution deep energy method with phase-field modeling of brittle fract…
MatReplace: A Reference-Free, Conditioning-Aligned Benchmark for Material Replacement in …
ACE: A Self-Correcting Agentic Canvas Editor for Multi-Slide Presentation Automation
The Sharp Tail of Uniform Stability
PARTAB: Partition-Aware Reasoning with Structured Evidence for Scalable Table Understandi…
Compression Trinity: Exploring Sparsity, Quantization, and Low-Rank Approximations for LL…
Representation Learning in Diffusion and Flow-based Model: An Application Aspect