CONTRAMEM: Learning Self-Evolving Procedural Memory from Contrasting Multi-Model Trajectories
Research
Research News
New papers, breakthroughs and academic AI research
What Makes Recurrence Effective in Looped Language Models?
Research
Replay the Curvature: Accurate and Scalable NVFP4 Quantization for Large Language Model Inference
Research
From Neurons to Conversation: Speech Brain-Computer Interfaces
Research
World-as-Graph: Relational World Modeling Through Latent Space Graphs
Research
EFormer: Temporally Aligned Local Correction for Continuous sEMG-Based Hand Pose Tracking
Research
Unlearning Deceptive Behaviors in LLMs with Contrastive Forget Sets
Research
Learning Where to Steer: Noise-Space Geometry for Efficient Offline Multi-Objective Optimization with Generative Models
Research
How Much of a Harness Does a Strong Agent Need for Autonomous ML Engineering?
Research
FrontierGS: Progressive View-Space Frontier Expansion for Sparse 3D Gaussian Splatting
Research
Flow Matching under Noisy Latent Structure: Beyond Exact Low-Dimensional Support
Research
Reconstructing the Vocal Tract with Differentiable Acoustic Simulation
Research