Learned, Lagged, LLM-splained: LLM Responses to End User Security Questions
"模型改进" 相关文章
What Defines Good Reasoning in LLMs? Dissecting Reasoning Steps with Multi-Aspect Evaluation
ColorBench: Benchmarking Mobile Agents with Graph-Structured Framework for Complex Long-Horizon Tasks
Towards Thinking-Optimal Scaling of Test-Time Compute for LLM Reasoning
Building a Foundational Guardrail for General Agentic Systems via Synthetic Data
Improving Temporal Understanding Logic Consistency in Video-Language Models via Attention Enhancement
Context Length Alone Hurts LLM Performance Despite Perfect Retrieval
Context Length Alone Hurts LLM Performance Despite Perfect Retrieval
Multimodal Carotid Risk Stratification with Large Vision-Language Models: Benchmarking, Fine-Tuning, and Clinical Insights
Format Inertia: A Failure Mechanism of LLMs in Medical Pre-Consultation
Hierarchical Reasoning Model: A Critical Supplementary Material
Echoes of Humanity: Exploring the Perceived Humanness of AI Music
Sea-ing Through Scattered Rays: Revisiting the Image Formation Model for Realistic Underwater Image Generation
Context Engineering for Trustworthiness: Rescorla Wagner Steering Under Mixed and Inappropriate Contexts
MIDOG 2025: Mitotic Figure Detection with Attention-Guided False Positive Correction
SampleAttention: Near-Lossless Acceleration of Long Context LLM Inference with Adaptive Structured Sparse Attention
ELV-Halluc: Benchmarking Semantic Aggregation Hallucinations in Long Video Understanding
GrAInS: Gradient-based Attribution for Inference-Time Steering of LLMs and VLMs
Bridging the Plausibility-Validity Gap by Fine-Tuning a Reasoning-Enhanced LLM for Chemical Synthesis and Discovery
Efficient Perplexity Bound and Ratio Matching in Discrete Diffusion Language Models
