37 citations · 37 across the 15 of their papers we have counts for
9 papers · 1 filter
StepAudio 3 Realtime Technical Report
Bin Lin, Bo Zhao, Boyang Zhang +87
Realtime spoken interaction demands deep reasoning, prompt responses, and fluid turn-taking. We present StepAudio 3 Realtime, an audio-language foundation model organized around a…
SCP-NL2TL: Selective Conformal Prediction with Semantic Verification for Natural Language to Temporal Logic Specifications
Yixuan Wang, Licheng Luo, Yu Fu +3
Translating natural language instructions into machine-interpretable formal specifications enables robots and autonomous systems to plan, reason, and formally verify their behavior…
Revise, Don't Freeze: Sampler-Matched Training for Self-Correcting Masked Diffusion Language Models
Longxuan Yu, Shaorong Zhang, Yu Fu +3
Masked diffusion language models (MDLMs) re-predict every position at each denoising step, but standard samplers commit tokens once revealed, leaving this revision capability unuse…
DSL-LLaDA: Scaling Continuous Denoising to 8B Masked Diffusion LMs
Longxuan Yu, Yunshu Wu, Yu Fu +5
Discrete Masked diffusion language models generate text by iterative parallel decoding, but few-step decoding suffers from a tradeoff between length and quality: with a fixed step…
Where and What to Reward? Understanding Generalization Between Verifiable and Open-Ended Domains in Reinforcement Learning
Shangjian Yin, Yu Fu, Yue Dong +1
Reinforcement learning with verifiable rewards (RLVR) is widely used to improve the reasoning capability of language models, since model-generated answers can be easily verified by…
Reducing the Safety Tax in LLM Safety Alignment with On-Policy Self-Distillation
Yu Fu, Longxuan Yu, Haz Sameen Shahgir +4
Safety alignment often improves robustness to harmful queries at the cost of reasoning ability, a tradeoff known as the safety tax. A common cause is distributional mismatch: super…
Overton Pluralistic Reinforcement Learning for Large Language Models
Yu Fu, Seongho Son, Ilija Bogunovic
Existing alignment paradigms remain limited in capturing the pluralistic nature of human values. Overton Pluralism (OP) addresses this gap by generating responses with diverse pers…
Do Reasoning LLMs Refuse What They Infer in Long Contexts?
Yu Fu, Haz Sameen Shahgir, Huanli Gong +3
Long-context LLMs can infer objectives that are not stated explicitly. This capability is useful for reasoning over documents, code, retrieved evidence, and tool traces, but it als…
Thinking Out of Order: When Output Order Stops Reflecting Reasoning Order in Diffusion Language Models
Longxuan Yu, Yu Fu, Shaorong Zhang +4
Autoregressive (AR) language models enforce a fixed left-to-right generation order, creating a fundamental limitation when the required output structure conflicts with natural reas…