Compile by Training: Turning Natural-Language Specifications into Local Neural Functions
Explorar
Noticias de IA
37834 elementos — filtrados, clasificados y sin duplicados
Remember and Reweight: Enhancing Multi-Agent Debate with Experience Memory and Confidence…
On the Interaction Between Model Compression and Test-Time Adaptation
Test-time adaptation for speech enhancement with an autoregressive speech prior
EraseSAE: Surgical Concept Erasure in Text-to-Video Diffusion Models via Sparse Autoencod…
From Prior-Guided Heuristics to Deployable Agents: Accelerating Demonstration-Driven Rein…
Beyond BLEU: A Case for Redefining Sign Language Translation Benchmarks
LevelSyn: Physical-Aware Logic Synthesis via Level-Asynchronous Graph Neural Networks
Building and Evaluating Fixed-Voice Thai TTS from Synthetic Speech
BRIDGE: An Open-Source Humanoid Platform via Morphology-Control Co-Design for Physical AI
Air-Ground Collaborative Vision-and-Language Navigation via Shared Bird's-Eye Maps
TruncGradGS: Improved 3D Gaussian Splatting via Truncated Gradient Updates
Plan Pointers and Record-Directive Form in Budgeted Verification of Inherited Agent Memory
The Psychological Costs of Artificial Intelligence Adoption in Software Engineering
It's the Problem, Not the Path: Budget and Difficulty Confounds in LLM Reasoning Trajecto…
The Civilization Framework: Sovereign-Anchored Communication Between Personal Multi-Agent…
When Users Don't Ask: Benchmarking Context-Driven Memory Retrieval in Conversational Agen…
Privacy, Robustness, and Fairness Trade-offs in Federated Intrusion Detection: Geometric …
ScoreMix: Synthetic Data Generation by Score Composition in Diffusion Models Improves Rec…
StrixAE: An Intelligent Agent for Audio Enhancement under Complex Distortion Coupling in …
Exploring the Potential of Contrastive Language-Image Pre-training for Multi-Source Remot…
WIDE: Wildcard Inference with Dynamic Expansion for Cross-Modal Generative Retrieval
Spectral Convergence of Random Feature Method in Multiple Dimensions
Verify Before You Distill: Prompt-Level Teacher Gating for On-Policy Distillation
ObserverBench: Testing Mechanistic Estimates for Intervention and Control
SHELF: A Synthetic Harness for Multi-Task Bibliographic Benchmarking
FlowBalance: Verifier-Grounded Self-Improvement from On-Policy Reasoning Experience
Headroom-Drift Replay: A Primitive for Principled Replay Control in GRPO
Reflect-SQL: A Self-Reflection Based Framework for Text-to-SQL
Judging LLM-as-a-Judge: Concerning Rubric Artifacts in LLM-based Automated Text Generatio…