11 papers
Reward-Gated On-Policy Distillation
Mohammad Sadegh Akhondzadeh, Vijay Lingam, Atula Tejaswi +3
On-policy distillation is a powerful way to transfer reasoning ability from a strong teacher to a smaller student: the student samples trajectories from its own policy, and the tea…
OmniSapiens: A Foundation Model for Social Behavior Processing via Heterogeneity-Aware Relative Policy Optimization
Keane Ong, Sabri Boughorbel, Luwei Xiao +9
Socially intelligent AI systems must reason across diverse human behavioral tasks and generalize to new social contexts. However, behavioral data is inherently heterogeneous, compr…
NeuroAtlas: Benchmarking Foundation Models for Clinical EEG and Brain-Computer Interfaces
Konstantinos Kontras, Trui Osselaer, Stylianos G. Mouslech +12
Foundation models (FMs) promise to extract unified representations that generalize across downstream tasks. They have emerged across fields, including electroencephalography (EEG),…
MURPHY: Feedback-Aware GRPO with Retrospective Credit Assignment for Multi-Turn Code Generation
Chanakya Ekbote, Vijay Lingam, Sujay Sanghavi +4
Reinforcement Learning with Verifiable Rewards (RLVR) has become a standard recipe for post-training LLMs on reasoning tasks, with Group Relative Policy Optimization (GRPO) emergin…
SCATR: Simple Calibrated Test-Time Ranking
Divya Shyamal, Marta KneževiÄ, Lan Tran +3
Test-time scaling (TTS) improves large language models (LLMs) by allocating additional compute at inference time. In practice, TTS is often achieved through parallel scaling: gener…
PuzzleWorld: A Benchmark for Multimodal, Open-Ended Reasoning in Puzzlehunts
Hengzhi Li, Justin Zhang, Brendon Jiang +9
Puzzlehunts are a genre of complex, multi-step puzzles lacking well-defined problem definitions. In contrast to conventional reasoning benchmarks consisting of tasks with clear ins…