N-GRPO: Embedding-Level Neighbor Mixing for Enhanced Policy Optimization (2026)
RL fine-tuning methods such as GRPO depend on the rollout phase producing varied reasoning paths. Existing approaches have drawbacks. Ordinary token sampling tends to produce near-duplicate solutions that differ only in wording or operand order. Adding Gaussian noise to embeddings, by contrast, often moves tokens to…
TingIS: Real-time Risk Event Discovery from Noisy Customer Incidents at Enterprise Scale (2026)
Large cloud-native and fintech services sometimes fail in ways that internal monitoring does not catch. Complaints from users can expose these failures early, but the complaints are colloquial, noisy, arrive in heavy streams and span many business lines. TingIS is an end-to-end system from Ant Group that turns this…
Verifier-Free RL for LLMs via Intrinsic Gradient-Norm Reward (2026)
Reinforcement learning with verifiable rewards (RLVR) works well for LLM post-training, but it needs gold answers or task-specific checkers, which limits its use in new domains.

Co-authors here

5 co-authors with a page, the most papers together first.

Venues

Where their works here were published, the most works first, with the editions of those that have a page.

Updated 2 November 2026