X-AuT: Progressive Audio-Encoder Compression for Speech LLMs with Cross-Scale Distillation
Explorar
Noticias de IA
27413 elementos — filtrados, clasificados y sin duplicados
A Time-Based Readout for Vector-Matrix Multiplication in Fully Analog Memristive SNNs
Structural priors for data-efficient language learning
Model-Aware Schedules Improve Generation via Fiberwise Optimal Transport
Physics-Informed Neural Networks to Infer the Perpendicular Energy Conductivity in the Sc…
TRUST-SQL: Tool-Integrated Multi-Turn Reinforcement Learning for Text-to-SQL over Unknown…
The Semantic Elevation Operator and the Closure of the Undecidable Class under Preservati…
Your Model Already Knows Don't Teach It, Learn to Ask It: Soft Prompting for Few-Shot Ada…
E-CONAN (Entailment, CONtradition And Neutral) Benchmarks: Arabic Textual Entailment and …
On the Impact of Anonymization on the Performance of Large Language Models
Improving Faint Object Detection for Space Situational Awareness with Variational Autoenc…
Generative Replay Mitigates Sample Starvation in Quantum Architecture Search
2AM: Grounding Agent-Side Memory as Guidance for Steerable Action Models in Long-Horizon …
(Whose defaults?) Is artificial intelligence reorienting archaeological methods?
Beyond Visual Quality: Evaluating Physical Consistency under Ego-Motion with EgoGenEval
X-RACE: XAI-assisted Recurrent neural network Attribution for Channel Estimation
From Evaluation to Enhancement: Benchmarking and Improving Think-with-Video Reasoning for…
A Fragility Spectrum for Recursive Language-Model Training
Characterizing Bluesky Content Moderation Service: From Automation of Service to Landscap…
BenchShield: Formal Model-Backed Instrumentation for Reward Integrity in LLM-Agent Evalua…
Less can be More: What Aspects of Speech Drive End-of-Turn Detection
Beyond Benchmarks: Using VLMs to Reveal Systematic Classification Failures Under Real Wor…
New Evidence, Same Choice: Testing Physical Experiment Selection in Vision Language Models
A Mathematical Theory of Pragmatic Information
Topological Necessities: Mechanism-Invariant Strategic Subgoals for Cross-Embodiment Goal…
ReactHuman: A Physics-Grounded Benchmark for Human-Like Reactive Decision-Making in Embod…
Tapes Together Strong: The Co-evolution of Computation and Cooperation
Robust Multimodal Sentiment Analysis with Incomplete Modalities via Semantic-aware Comple…
When Synthetic Data Hurts: On Catastrophic Forgetting in Skill Retrieval for LLM Agents
What a Random Draw from the MCP Registry Contains, and What Tool-Use Benchmarks Contain I…