When, Not How Much: Evaluating Time-Series Foundation Models on Sparse Events
Research
Research News
New papers, breakthroughs and academic AI research
Beyond Simulation: Retain-and-Repair Neural Operators for Real-World Adaptation
Research
Network-based Spatial Context Retrieval for Open-weight LLMs: A Faithfulness Benchmark for Grounded Geographic Reasoning
Research
Hiding in Plain Sight: Decoupling Pretext from Actuation for Skill Poisoning in LLM Agents
Research
Reproducing, Analyzing, and Detecting Reward Hacking in Rubric-Based Reinforcement Learning
Research
MCD: Causal Distillation of Multimodal In-Context Learning in Large Vision-Language Models
Research
CORE-BREW: LLR-Based Soft Decoding for Robust Multi-Bit LLM Watermarking
Research
HPRO: Hierarchical Progressive Reward Optimization via Preference Extraction for Emotional Text-to-Speech
Research
Decoupled and Distilled: Task-Adaptive LoRA-Teachers with Ensemble Knowledge Transfer for Few-Shot Class-Incremental Learning
Research
Awakening of the Buddha: Subspace Learning During Population-Loss Plateaus
Research
QuantCode Model: Specializing Language Models for Executable Algorithmic Trading Code
Research
Super-Resolving Unseen Hyperspectral Sensors at Any Scale via Spatial Operators
Research