DeepSeek AI has unveiled DeepSeek-OCR, a groundbreaking approach to compressing long contexts via optical 2D mapping. This innovative system demonstrates that vision-based compression can achieve rema

· Claim: Decoder‑only transformer LMs are almost‑surely injective: different prompts map to unique last‑token hidden states; this holds at initialization and is preserved under gradient descent. · Met

Instead of simulating clicks and scrolls, researchers let LLMs reason which playlist, feed, or product lineup you’d actually prefer. And it worked. Across Amazon, Spotify, MovieLens, and MIND datasets

This paper got top score at NeurIPS 2025. It aims at answering: does RL make LLM better reasoners? The authors study Reinforcement Learning with Verifiable Rewards RLVR and find that while it improves

Tencent + Tsinghua just dropped a paper called Continuous Autoregressive Language Models CALM and it basically kills the “next-token” paradigm every LLM is built on. Instead of predicting one token at

Perplexity in NLP measures how well a language model predicts text; lower means better.