Skip to yearly menu bar Skip to main content


(7 events)   Timezone:  
Show all
Toggle Poster Visibility
Oral
Thu Apr 23 11:15 AM -- 11:25 AM (PDT) @ Amphitheater None
LongWriter-Zero: Mastering Ultra-Long Text Generation via Reinforcement Learning
In Oral Session 2A Reinforcement learning I
Yuhao Wu ⋅ Yushi Bai ⋅ Zhiqiang Hu ⋅ Roy Ka-Wei Lee ⋅ Juanzi Li
[ OpenReview] 
Oral
Thu Apr 23 11:27 AM -- 11:37 AM (PDT) @ Amphitheater None
EmotionThinker: Prosody-Aware Reinforcement Learning for Explainable Speech Emotion Reasoning
In Oral Session 2A
Dingdong WANG · Shujie LIU · Tianhua Zhang · Youjun Chen · Jinyu Li · Helen Meng
[ OpenReview] 
Oral
Thu Apr 23 11:39 AM -- 11:49 AM (PDT) @ Amphitheater None
Token-Importance Guided Direct Preference Optimization
In Oral Session 2A Reinforcement learning I
Ning Yang ⋅ Hai Lin ⋅ Yibo Liu ⋅ Baoliang Tian ⋅ Guoqing Liu ⋅ Haijun Zhang
[ OpenReview] 
Oral
Thu Apr 23 11:51 AM -- 12:01 PM (PDT) @ Amphitheater None
P-GenRM: Personalized Generative Reward Model with Test-time User-based Scaling
In Oral Session 2A Reinforcement learning I
Pinyi Zhang ⋅ Ting-En Lin ⋅ Yuchuan Wu ⋅ Jingyang Chen ⋅ Zongqi Wang ⋅ Hua Yang ⋅ Bing Zhao ⋅ Fei Huang ⋅ Yongbin Li ⋅ Kai Zhang
[ Slides]  [ OpenReview] 
Oral
Thu Apr 23 12:03 PM -- 12:13 PM (PDT) @ Amphitheater None
Reasoning with Sampling: Your Base Model is Smarter Than You Think
In Oral Session 2A Reinforcement learning I
Aayush Karan ⋅ Yilun Du
[ Slides]  [ OpenReview] 
Oral
Thu Apr 23 12:15 PM -- 12:25 PM (PDT) @ Amphitheater None
LoongRL: Reinforcement Learning for Advanced Reasoning over Long Contexts
In Oral Session 2A Reinforcement learning I
Siyuan Wang ⋅ Gaokai Zhang ⋅ Li Lyna Zhang ⋅ Ning Shang ⋅ Fan Yang ⋅ Dongyao Chen ⋅ Mao Yang
[ Slides]  [ OpenReview] 
Oral
Thu Apr 23 12:27 PM -- 12:37 PM (PDT) @ Amphitheater None
Q-RAG: Long Context Multi‑Step Retrieval via Value‑Based Embedder Training
In Oral Session 2A Reinforcement learning I
Artyom Sorokin ⋅ Nazar Buzun ⋅ Aleksandr Anokhin ⋅ Egor VEDERNIKOV ⋅ Petr Anokhin ⋅ Mikhail Burtsev ⋅ Evgeny Burnaev
[ Slides]  [ OpenReview]