Plus more about RL Finetunes Small Subnetworks in LLMs and Multimodal Large Diffusion LMs
Plus more about Parallel Scaling Law for Language Models and faster matrix multiplications
Premium Insights: A closer look into the DeepSeek Prover series
Plus more about Ming-Lite-Uni: Advancements in Unified Architecture for Natural Multimodal Interaction and RM-R1: Reward Modeling as Reasoning
Plus more about Phi-4-reasoning Technical Report and Softpick: No Attention Sink, No Massive Activations with Rectified Softmax
Premium Insights: A recap of popular AI research papers and research trends in April 2025
Plus more about Process Reward Models That Think and PHYBench: Holistic Evaluation of Physical Perception and Reasoning in Large Language Models
Plus more about BitNet b1.58 2B4T Technical Report and ReTool: Reinforcement Learning for Strategic Tool Use in LLMs
Plus more about One-Minute Video Generation with Test-Time Training and Gaussian Mixture Flow Matching Models
Plus more about Inference-Time Scaling for Generalist Reward Modeling and Why do LLMs attend to the first token?
Plus more about Defeating Prompt Injections by Design and Reasoning to Learn from Latent Thoughts
Plus more about RWKV-7 "Goose" with Expressive Dynamic State Evolution and Measuring AI Ability to Complete Long Tasks
