DPBench: Structural Determinants of Multi-Agent LLM Coordination Under Simultaneous Resou…
Explorar
Noticias de IA
22065 elementos — filtrados, clasificados y sin duplicados
UniVoice: A Unified Model for Speech and Singing Voice Generation
Compositional Boundaries for Density Fusion
Controllable and Verifiable Process Data Synthesis for Process Reward Models
To Be Multimodal or Not to Be: Query-Adaptive Audio-Visual Person Retrieval via Active Mo…
ArcANE: Do Role-Playing Language Agents Stay in Character at the Right Time?
Scaling Laws and Spectra of Shallow Neural Networks in the Feature Learning Regime
Drive-KD: Multi-Teacher Distillation for VLMs in Autonomous Driving
SciVisAgentSkills: Design and Evaluation of Agent Skills for Scientific Data Analysis and…
Towards One-to-Many Temporal Grounding
Breaking the Chain: A Causal Analysis of LLM Faithfulness to Intermediate Structures
The Topological Trouble With Transformers
Open-H-Embodiment: A Large-Scale Dataset for Enabling Foundation Models in Medical Roboti…
The Virtual Roundtable: Multi-Agent Personas Simulating the Dynamics of Human Brainstormi…
InfoDensity: Rewarding Information-Dense Traces for Efficient Reasoning
PAMF: Prior-Aware Multimodal Fusion for Incomplete Time Series Data
TOKI: A Bitemporal Operator Algebra for Contradiction Resolution in LLM-Agent Persistent …
RAS: a Reliability Oriented Metric for Automatic Speech Recognition
Subspace-Aware Sparse Autoencoders for Effective Mechanistic Interpretability
F3-Tokenizer: Taming Audio Autoencoder Latents for Understanding and Generation
Benchmarking Emergent Coordination in Large-Scale LLM Populations: An Evaluation Framewor…
LatentWave: JEPA Pretraining for Wireless Foundation Models
ReTreVal: Reasoning Tree with Validation and Cross-Problem Memory for Large Language Mode…
MARDoc: A Memory-Aware Refinement Agent Framework for Multimodal Long Document QA
CoT-Space: A Theoretical Framework for Internal Slow-Thinking via Reinforcement Learning
Beyond Vector Similarity: A Structural Analysis of Graph-Augmented Retrieval for Industri…
Do Models Share Safety Representations? Cross-Model Steering for Safe Visual Generation
TempoVLA: Learning Speed-Controllable Vision-Language-Action Policies
In-Training Defenses against Emergent Misalignment in Language Models
Detecting Perspective Shifts in Multi-agent Systems