LOVER creates an unsupervised logic-regularized verifier that reaches 95% of supervised verifier performance on reasoning tasks across 10 datasets.
hub
Advances in Neural Information Processing Systems , volume=
10 Pith papers cite this work. Polarity classification is still indexing.
10
Pith papers citing it
hub tools
representative citing papers
OptiVerse is a new benchmark spanning neglected optimization domains that shows LLMs suffer sharp accuracy drops on hard problems due to modeling and logic errors, with a Dual-View Auditor Agent proposed to improve performance.
Listwise Policy Optimization explicitly performs target-projection on the LLM response simplex, unifying and improving group-based RLVR methods with monotonic improvement and flexible divergences.
HEAL mitigates entropy collapse in few-shot RLVR by selectively adding general-domain data and aligning trajectory-level entropy dynamics, matching full-shot performance with 32 target samples.
LIMO achieves 63.3% on AIME24 and 95.6% on MATH500 via supervised fine-tuning on roughly 1% of the data used by prior models, supporting the claim that minimal strategic examples suffice when pre-training has already encoded domain knowledge.
PRIME enables online process reward model updates in LLM RL using implicit rewards from rollouts and outcome labels, yielding 15.1% average gains on reasoning benchmarks and surpassing a stronger instruct model with 10% of the data.
SmolLM2 is a 1.7B-parameter language model that outperforms Qwen2.5-1.5B and Llama3.2-1B after overtraining on 11 trillion tokens using custom FineMath, Stack-Edu, and SmolTalk datasets in a multi-stage pipeline.
Step-Video-T2V describes a 30B-parameter text-to-video model with custom Video-VAE, 3D DiT, flow matching, and Video-DPO that claims state-of-the-art results on a new internal benchmark.