SharpDraft: Accelerating Long-Context Speculative Decoding with Cardinality-Aware Query Scaling
Research
Research News
New papers, breakthroughs and academic AI research
Memory Canonicalization: A Framework and Benchmark for Cross-Model Drift in Persistent LLM Memory
Research
Memadapter: Counterfactual Adaptation Against Memory-induced Sycophancy
Research
Coupling Noisy Pairwise Knowledge to the DAG Posterior for Causal Discovery
Research
CLARA: Can AI Assess Developmental Appropriateness in Children's Stories?
Research
PWM: Personalized World Models with Online Reinforcement Learning
Research
Robust Tensor Completion via Reflective Convolution Nuclear Norm Minimization
Research
VisualErase: Dual-Branch Visual Trajectory Redirection for Robust Concept Erasure in Text-to-Image Diffusion Models
Research
Only Project Once: Projection-Adaptive Loss for Exact Constraint Satisfaction
Research
Look Before You Leap: Thermodynamic Arbitration of Parametric and Non-Parametric Knowledge in LLM Agents via Self-Regulating Memory Architectures
Research
LexiHorizon: Stabilizing Reinforcement Learning for Long-Horizon Deep Search
Research
AutoSciBench: Autonomous Benchmark Generation for Evaluating Scientific Agents
Research