DART-ES: Difficulty-Aware Reweighting and Targeted Replay for Fine-Tuning LLMs with Evolution Strategies
Research
Research News
New papers, breakthroughs and academic AI research
FluidPD: In-Place Elasticity for SLO-Aware Prefill-Decode Disaggregated LLM Serving
Research
Learning to Decide, Not to Reason: Parameter-Efficient Decision Operators via Low-Rank Activation Steering
Research
Mask-Guided KV Cache Eviction in Block Diffusion Language Models
Research
Scalable Decision Making for Games of Imperfect Information
Research
The Universal Weight Subspace Hypothesis
Research
TIDE 2.0: an open, model-agnostic engine for keyed de-identification of clinical notes
Research
RadOnc-Agent: An LLM-Orchestrated Framework for AI Workflows Across the Radiotherapy Care Pathway
Research
CuratorMAS: Automating Dataset Curation via Multi-Agent Orchestration
Research
Do Neural PDE Solvers Learn the Right Dynamics?
Research
An Information-Theoretic Evaluation Framework for Benchmark and Model Diagnosis in Knowledge Tracing
Research
Bi-objective chance-constrained evolutionary optimization for large-scale open-pit mine scheduling under geological uncertainty
Research