2 papers
cs.CV2026
SPHINX: A Synthetic Environment for Visual Perception and Reasoning
Md Tanvirul Alam, Saksham Aggarwal, Justin Yang Chae +1
We present Sphinx, a synthetic environment for visual perception and reasoning that targets core cognitive primitives. Sphinx procedurally generates puzzles using motifs, tiles, ch…
cs.LG2025
Towards Understanding Self-play for LLM Reasoning
Justin Yang Chae, Md Tanvirul Alam, Nidhi Rastogi
Recent advances in large language model (LLM) reasoning, led by reinforcement learning with verifiable rewards (RLVR), have inspired self-play post-training, where models improve b…