1 citations · 1 across the 10 of their papers we have counts for
12 papers
TRACER: Trajectory-Aligned Learning for Multi-Turn User Simulation
Geng Chen, Ruotong Pan, Zhirui Yang +9
Faithful user simulation is fundamental to building, evaluating, and improving interactive AI at scale. Yet current simulators often produce plausible individual responses without…
OneReason Technical Report
OneRec Team, Biao Yang, Boyang Ding +81
Generative recommendation models in the OneRec family have been widely deployed in many real-world services, such as short-video, live-streaming, advertising, and e-commerce. Howev…
GoLongRL: Capability-Oriented Long Context Reinforcement Learning with Multitask Alignment
Minxuan Lv, Tiehua Mei, Tanlong Du +9
We present GoLongRL, a fully open-source, capability-oriented post-training recipe for long-context reinforcement learning with verifiable rewards (RLVR). Existing long-context RL…
Kwai Summary Attention Technical Report
Chenglong Chu, Guorui Zhou, Guowang Zhang +35
Long-context ability, has become one of the most important iteration direction of next-generation Large Language Models, particularly in semantic understanding/reasoning, code agen…
Good Reasoning Makes Good Demonstrations: Implicit Reasoning Quality Supervision via In-Context Reinforcement Learning
Tiehua Mei, Minxuan Lv, Leiyu Pan +5
Reinforcement Learning with Verifiable Rewards (RLVR) improves reasoning in large language models but treats all correct solutions equally, potentially reinforcing flawed traces th…
Entropy Ratio Clipping as a Soft Global Constraint for Stable Reinforcement Learning
Zhenpeng Su, Leiyu Pan, Minxuan Lv +7
Large language model post-training relies on reinforcement learning to improve model capability and alignment quality. However, the off-policy training paradigm introduces distribu…
CE-GPPO: Coordinating Entropy via Gradient-Preserving Clipping Policy Optimization in Reinforcement Learning
Zhenpeng Su, Leiyu Pan, Minxuan Lv +5
Reinforcement learning (RL) has become a powerful paradigm for optimizing large language models (LLMs) to handle complex reasoning tasks. A core challenge in this process lies in m…
Finedeep: Mitigating Sparse Activation in Dense LLMs via Multi-Layer Fine-Grained Experts
Leiyu Pan, Zhenpeng Su, Minxuan Lv +10
Large language models have demonstrated exceptional performance across a wide range of tasks. However, dense models usually suffer from sparse activation, where many activation val…
DSMoE: Matrix-Partitioned Experts with Dynamic Routing for Computation-Efficient Dense LLMs
Minxuan Lv, Zhenpeng Su, Leiyu Pan +10
As large language models continue to scale, computational costs and resource consumption have emerged as significant challenges. While existing sparsification methods like pruning…
CartesianMoE: Boosting Knowledge Sharing among Experts via Cartesian Product Routing in Mixture-of-Experts
Zhenpeng Su, Xing Wu, Zijia Lin +6
Large language models (LLM) have been attracting much attention from the community recently, due to their remarkable performance in all kinds of downstream tasks. According to the…
CT-GAT: Cross-Task Generative Adversarial Attack based on Transferability
Minxuan Lv, Chengwei Dai, Kun Li +2
Neural network models are vulnerable to adversarial examples, and adversarial transferability further increases the risk of adversarial attacks. Current methods based on transferab…
MeaeQ: Mount Model Extraction Attacks with Efficient Queries
Chengwei Dai, Minxuan Lv, Kun Li +1
We study model extraction attacks in natural language processing (NLP) where attackers aim to steal victim models by repeatedly querying the open Application Programming Interfaces…