TopK-Guided: Adaptive, Budget-Aware Activation Sparsity for Efficient LLM Inference
Research
Research News
New papers, breakthroughs and academic AI research
Group-Invariant Statistics Determine Embedding Geometry: Harmonic Analysis of Representations from Bach to the Night Sky
Research
On the Divergence of Accuracy and Mechanism Consistency in Time Series World Models
Research
Dyna3: VLM-Guided Training-Free 4D Reconstruction via Depth Foundation Models
Research
STAGE: Subspace-Targeted Affine Generative Erasure for Text-to-3D Models
Research
Exploring More, Reasoning Better: Stepwise Risk-Sensitive GRPO for Diffusion Language Models
Research
Analysis of Quantized and Efficiently Adapted Protein Language Models
Research
Mapping the RAG Landscape: A Four Axis Taxonomy of Efficiency, Defense, Interactivity, and Reasoning
Research
Can AI Oversight Be Zero Knowledge?
Research
Q-Learning for Reachability in MEC-Free MDPs
Research
Not All Experience Belongs in the Weights: Component Routing for Self-Improving GUI Agents
Research
Temporal-Difference Learning for Dragonchess
Research