3 citations · 4 across the 30 of their papers we have counts for
32 papers
MAS-OPD: On-Policy Distillation for Multi-agent Systems
Qiyong Zhong, Mao Zheng, Mingyang Song +5
Multi-agent systems (MAS) split a task across specialized roles and are promising on complex tasks, yet a prevailing approach relies on inference-time orchestration alone. General-…
USA: Update-aware SAM for Cross-domain On-Policy Disitllation of Language Agents
Qiyong Zhong, Mao Zheng, Mingyang Song +6
On-policy distillation instils multi-turn agentic reasoning through dense token-level supervision on the student's own trajectories, but a single domain saturates early, so further…
Distill What You Trust: Reliability-Aware Multi-Teacher On-Policy Distillation
Jie Sun, Mao Zheng, Mingyang Song +8
Multi-teacher on-policy distillation allows a student to learn from complementary specialists on its own trajectories. Domain-routed approaches, however, select one teacher per exa…
EasyOPD: An Easy-to-use On-Policy Distillation Framework for Large Language Models
Jie Sun, Mao Zheng, Mingyang Song +7
Conventional language-model distillation often relies on fixed teacher-generated data, which may not cover the states encountered by an evolving student policy. On-policy distillat…
On-Policy Distillation with Curriculum Turn-level Guidance for Multi-turn Agents
Gengsheng Li, Mao Zheng, Mingyang Song +8
Multi-turn agents that plan, invoke tools, and interact with environments offer a promising paradigm for solving complex tasks, yet their capabilities typically rely on very large…
Memory Beyond Recall: A Dual-Process Cognitive Memory System for Self-Evolving LLM Agents
Tianxiang Fei, Mingyang Song, Mao Zheng +1
Long-term memory for an LLM agent is more than retrieving the right passage at the right time. Current memory systems collapse belief revision, causal coupling, and cross-domain ab…
HardMTBench: Stress-Testing Chinese-English Translation on Knowledge-Intensive Domains
Zheng Li, Mao Zheng, Mingyang Song +1
General-purpose machine translation benchmarks such as FLORES-200 have reached a saturation regime on Chinese-English pairs, where modern large language models cluster within a nar…
IFMTBench: A Comprehensive Benchmark for Multilingual Translation Instruction Following
Mingrui Sun, Mao Zheng, Zheng Li +1
Modern translation workflows demand more than semantic equivalence. Users routinely require models to preserve JSON or HTML schemas, honor curated glossaries, disambiguate with pro…
Hy-MT2: A Family of Fast, Efficient and Powerful Multilingual Translation Models in the Wild
Mao Zheng, Zheng Li, Tao Chen +10
Hy-MT2 is a family of fast-thinking multilingual translation models designed for complex real-world scenarios. It includes three model sizes: 1.8B, 7B, and 30B-A3B (MoE), all of wh…
SimCT: Recovering Lost Supervision for Cross-Tokenizer On-Policy Distillation
Jie Sun, Mao Zheng, Mingyang Song +6
On-policy distillation (OPD) is a standard tool for transferring teacher behavior to a smaller student, but it implicitly assumes that teacher and student predictions are comparabl…
Rubric-based On-policy Distillation
Junfeng Fang, Zhepei Hong, Mao Zheng +7
On-policy distillation (OPD) is a powerful paradigm for model alignment, yet its reliance on teacher logits restricts its application to white-box scenarios. We contend that struct…
SOD: Step-wise On-policy Distillation for Small Language Model Agents
Qiyong Zhong, Mao Zheng, Mingyang Song +5
Tool-integrated reasoning (TIR) is difficult to scale to small language models due to instability in long-horizon tool interactions and limited model capacity. While reinforcement…
Unifying Group-Relative and Self-Distillation Policy Optimization via Sample Routing
Gengsheng Li, Tianyu Yang, Junfeng Fang +6
Reinforcement learning with verifiable rewards (RLVR) has become a standard paradigm for post-training large language models. While Group Relative Policy Optimization (GRPO) is wid…
PRISM: Probability Reallocation with In-Span Masking for Knowledge-Sensitive Alignment
Chenning Xu, Mao Zheng, Mingyang Song
Supervised fine-tuning (SFT) with token-level hard labels can amplify overconfident imitation of factually unsupported targets, causing hallucinations that propagate in multi-sente…
A Survey of On-Policy Distillation for Large Language Models
Mingyang Song, Mao Zheng
On-Policy Distillation (OPD) trains large language models with teacher guidance on student-generated trajectories, addressing the mismatch between fixed demonstrations and the hist…
Unify-Agent: A Unified Multimodal Agent for World-Grounded Image Synthesis
Shuang Chen, Quanxin Shou, Hangting Chen +16
Unified multimodal models provide a natural and promising architecture for understanding diverse and complex real-world knowledge while generating high-quality images. However, the…
Model Merging in the Era of Large Language Models: Methods, Applications, and Future Directions
Mingyang Song, Mao Zheng
Model merging combines the parameters of multiple neural networks into a single model without additional training. As fine-tuned large language models (LLMs) proliferate, merging o…
Beyond the Illusion of Consensus: From Surface Heuristics to Knowledge-Grounded Evaluation in LLM-as-a-Judge
Mingyang Song, Mao Zheng, Chenning Xu
The paradigm of LLM-as-a-judge relies on a critical assumption, namely that high inter-evaluator agreement indicates reliable and objective evaluation. We present two complementary…
CodeDelegator: Mitigating Context Pollution via Role Separation in Code-as-Action Agents
Tianxiang Fei, Cheng Chen, Yue Pan +2
Recent advances in large language models (LLMs) allow agents to represent actions as executable code, offering greater expressivity than traditional tool-calling. However, real-wor…
PodBench: A Comprehensive Benchmark for Instruction-Aware Audio-Oriented Podcast Script Generation
Chenning Xu, Mao Zheng, Mingyu Zheng +1
Podcast script generation requires LLMs to synthesize structured, context-grounded dialogue from diverse inputs, yet systematic evaluation resources for this task remain limited. T…
HY-MT1.5 Technical Report
Mao Zheng, Zheng Li, Tao Chen +2
In this report, we introduce our latest translation models, HY-MT1.5-1.8B and HY-MT1.5-7B, a new family of machine translation models developed through a holistic training framewor…
Hunyuan-MT Technical Report
Mao Zheng, Zheng Li, Bingxin Qu +4
In this report, we introduce Hunyuan-MT-7B, our first open-source multilingual translation model, which supports bidirectional translation across 33 major languages and places a sp…
Walk Before You Run! Concise LLM Reasoning via Reinforcement Learning
Mingyang Song, Mao Zheng
As test-time scaling becomes a pivotal research frontier in Large Language Models (LLMs) development, contemporary and advanced post-training methodologies increasingly focus on ex…
TAT-R1: Terminology-Aware Translation with Reinforcement Learning and Word Alignment
Zheng Li, Mao Zheng, Mingyang Song +1
Recently, deep reasoning large language models(LLMs) like DeepSeek-R1 have made significant progress in tasks such as mathematics and coding. Inspired by this, several studies have…