IrekoGPT: Turning Structured Pruning into Post-Hoc Slimmable LLMs
Research
Research News
New papers, breakthroughs and academic AI research
Every Batch Is Its Own Validation Set: Leave-One-Out Gradient Matching for Online Data Selection in LLM Fine-Tuning
Research
Exact information accounting for SGD methods
Research
Gumbel Straight Flow: Distilling Autoregressive Models into One-step Flow Maps
Research
PPO-HRAP: Proximal Policy Optimization with a Hybrid Regime-Aware Policy for Risk-Controlled Trading
Research
Verify Claims, Not Scores: Evidence-Based Verification of Modular Agents
Research
Gacha Decoding: Eliciting Diverse Generations Through Instruction Following
Research
Science Utopia? Closed-Loop LLM Simulation of Academic Research Ecosystems
Research
Bootstrapping Video Interaction Generation with Synthetic State Transitions
Research
HierGF: Hierarchical Gaussian Fields via Geometry-perception Message Passing for Sparse-view 3D Reconstruction
Research
Ego2Act: Evaluating Goal-Directed Manipulation in Egocentric Video Generation
Research
Affine-Aligned Atlas for Canonical Gaussian Construction in Video Representation
Research