LAPO: Leave-One-Turn Attribution for Self-Generated Process Rewards in Multi-Turn Search …
Explorar
Noticias de IA
27413 elementos — filtrados, clasificados y sin duplicados
Bring Music The Horizon: Music-Driven 360$^\circ$ Video Generation
PQFA: Parallel Quantum Feature Augmentation of Fused Representations for Multimodal Class…
LPM: Industrial-Scale Generative Video Restoration
GeoAnchor: Collaborative Reasoning via Latent Decomposition for 3D Spatial Understanding
Discrete Diffusion Models: A Unified Framework from Tokenization to Generation
MultiAnimate: A Unified Framework for Controllable Multi-Character Animation
Is the Statistical Advantage Worth the Cost? An Empirical Comparison of KANs and MLPs for…
Price of Fairness in Bandits: A Tight Minimax Characterization
Demystifying On-Policy Distillation: Roles, Pathologies, and Regulations
Set-shifting Behavioral Test for Harnessed Agents
Learning Engagement Assistant (LEA): Cross-Course Scalability and Classroom Evaluation of…
The Refusal Residue: When Probes Catch Alignment Faking and When They Don't
Audio-Text Cross-Attention with Psycholinguistic Support Features for Ambivalence/Hesitan…
Marker-free deformable registration and fusion for augmented reality-guided positive marg…
Finding the Right Tables and Columns: A Benchmark and Corpus-Adaptive Embeddings for SQL …
GSM-Plus-BN: A Perturbation-Based Benchmark for Bangla Mathematical Reasoning in Large La…
Reassessing Muon for Matrix Factorization
Hierarchical $\mathcal{F}$-Clustering: Approximation and Hardness of Clustering into Tree…
Self-Supervised Visual Representation Learning: Pretrain-Finetuning or Joint Training?
Concurrent Image Understanding and Generation: Self-Correcting Coupled Markov Jump Proces…
The Seriality Gap in Video Diffusion Models
A Shortcut to Statistically Steady-State Turbulence with Flow Matching
FlowWAM: Optical Flow as a Unified Action Representation for World Action Models
Audio-Native Speech Recognition with a Frozen Discrete-Diffusion Language Model
DermDepth: Toward Monocular Metric Scale 3D Reconstruction Models for Dermatology
Controllable Generation of Diverse Dermatological Imagery for Fair and Efficient Malignan…
Resist and Update: Counterfactual Report Coordinates for Incentive-Compatible LLMs
Ensemble Controlled-Flow Filtering for Implicit Data Assimilation
The Illusion of Robustness: Aggregate Accuracy Hides Prediction Flips under Task-Irreleva…