Topic Matching in the Wild: Benchmark and Lessons from Real-World ASR Transcripts
Explorar
Noticias de IA
27413 elementos — filtrados, clasificados y sin duplicados
FedReview: Review and Dispose Poisoned Updates without Validation Datasets or Historic Kn…
SCAFFOLD: A Large-Scale Structured Dataset of Computer Science Research Figures with Diag…
Flawed in Nature, Perfect through Evolution
Assessing Suicide Risk in Arabic Crisis Helpline Calls: A Comparison of Arabic and Englis…
RestoreBench: Can AI Agents Restore Power Flow Convergence?
mimeo: Compiling Public Expert Corpora into Agent Skills and Testing What Transfers
Detecting Hidden Behaviors in LLMs via Activation-matched Finetuning
Faster Than Flash: Exploiting Attention Sparsity for Efficient Long-Context Decoding
Do General NLP Embeddings Capture Ontological Reasoning?
AutoXRD: Autonomous LLM Agents and Comprehensive Evaluation for Powder Diffraction Analys…
KItCAT: Knowledge Injection via Input Corruption for Auto-regressive Training
Life Operators: a self-evolving framework for multiscale life modelling
Attention Sensitivity Is Not Enough: Dissociating Attention-Level and Behavioural In-Cont…
Scientific Agent Skills: A Library of Procedural Knowledge for Research Agents
OCGQuant: Outlier-Companion Grouping for NVFP4 Quantization
HEAL: Hindsight Entropy-Assisted Learning for Reasoning Distillation
Electronic Navigational Chart Change Classification
FLaG: Frequency-Domain Latent-attention Gated Pooling for Token Aggregation
Retrieval, Scoring, and Decoding Shape Performance and Stability in LLM-based Conversatio…
Multi-Agent LLM Orchestration Achieves Deterministic, High-Quality Decision Support for I…
HugAgent: A Human Simulation Benchmark for Individual-Level Reasoning
Revealing Multi-View Hallucination in Large Vision-Language Models
One-shot Style Transfer LLM log-probabilities for Authorship Attribution and Verification
A Human-AI Theorem Connecting Spontaneous and Field-Induced Mechanisms of Collective Beha…
Latent Recurrent Thoughts: Recurrent Refinement of Proposed Latents for Reasoning with Fr…
Scaling Near-Optimal SFT-RL Annotation Budget Allocation from Small to Large LLMs
Counterfactual Fragility Certificates: Exposing High-Confidence Brittleness under Structu…
ARISE-RL: Agentic Rubric-Grounded Iterative Self-Evolution with Reinforcement Learning
Dependency-Aware Chain-of-Thought Compression for Financial Reasoning