11 papers
UniJev: Separating Accuracy from Calibration in Trimodal System One Decision Models
Jianing Wang, Youwen Jian, Derong Wang +5
System One models produce probabilistic judgments that software can consume directly, making reliable confidence as important as answer accuracy. Yet joint training across text, im…
EMAS: Stabilizing Multi-Agent System Evolution through Evidence-Guided Revision
Chao Fei, Qingyi Si, Kaihua Liang +3
Many methods for automated multi-agent system design optimize prompts and topologies during an initial design stage and then deploy the resulting system unchanged on subsequent sam…
When Agents Evolve, Institutions Follow
Chao Fei, Hongcheng Guo, Yanghua Xiao
Across millennia, complex societies have faced the same coordination problem of how to organize collective action among cognitively bounded and informationally incomplete individua…
On the Trainability of Masked Diffusion Language Models via Blockwise Locality
Yuxiang Wang, Yu Xiang, Baojian Zhou +4
Masked diffusion language models (MDMs) have recently emerged as a promising alternative to standard autoregressive large language models (AR-LLMs), yet their optimization can be s…
Logics-STEM: Empowering LLM Reasoning via Failure-Driven Post-Training and Document Knowledge Enhancement
Mingyu Xu, Cheng Fang, Keyue Jiang +16
We present Logics-STEM, a state-of-the-art reasoning model fine-tuned on Logics-STEM-SFT-Dataset, a high-quality and diverse dataset at 10M scale that represents one of the largest…
Outcome-Grounded Advantage Reshaping for Fine-Grained Credit Assignment in Mathematical Reasoning
Ziheng Li, Liu Kang, Feng Xiao +7
Group Relative Policy Optimization (GRPO) has emerged as a promising critic-free reinforcement learning paradigm for reasoning tasks. However, standard GRPO employs a coarse-graine…
Accelerated Evolving Set Processes for Local PageRank Computation
Binbin Huang, Luo Luo, Yanghua Xiao +2
This work proposes a novel framework based on nested evolving set processes to accelerate Personalized PageRank (PPR) computation. At each stage of the process, we employ a localiz…
From Text to Trajectories: GPT-2 as an ODE Solver via In-Context
Ziyang Ma, Baojian Zhou, Deqing Yang +1
In-Context Learning (ICL) has emerged as a new paradigm in large language models (LLMs), enabling them to perform novel tasks by conditioning on a few examples embedded in the prom…
Fast and Robust Contextual Node Representation Learning over Dynamic Graphs
Xingzhi Guo, Silong Wang, Baojian Zhou +2
Real-world graphs grow rapidly with edge and vertex insertions over time, motivating the problem of efficiently maintaining robust node representation over evolving graphs. Recent…
Iterative Methods via Locally Evolving Set Process
Baojian Zhou, Yifan Sun, Reza Babanezhad Harikandeh +3
Given the damping factor and precision tolerance , \citet{andersen2006local} introduced Approximate Personalized PageRank (APPR), the \textit{de facto local method} for appr…
Faster Local Solvers for Graph Diffusion Equations
Jiahe Bai, Baojian Zhou, Deqing Yang +1
Efficient computation of graph diffusion equations (GDEs), such as Personalized PageRank, Katz centrality, and the Heat kernel, is crucial for clustering, training neural networks,…