1 citations · 2 across the 16 of their papers we have counts for
16 papers
Efficient and Trainable Language Model Test-Time Scaling via Local Branch Routing
Yutong Yin, Mingyu Jin, Jin Pan +12
Test-time scaling improves language-model reasoning, but existing approaches often face a difficult trade-off: long chain-of-thought sampling remains single-threaded, while sentenc…
Graph-based Agent Memory: Taxonomy, Techniques, and Applications
Chang Yang, Chuang Zhou, Yilin Xiao +15
Memory emerges as the core module in the Large Language Model (LLM)-based agents for long-horizon complex tasks (e.g., multi-turn dialogue, game playing, scientific discovery), whe…
Augmenting Intra-Modal Understanding in MLLMs for Robust Multimodal Keyphrase Generation
Jiajun Cao, Qinggang Zhang, Yunbo Tang +3
Multimodal keyphrase generation (MKP) aims to extract a concise set of keyphrases that capture the essential meaning of paired image-text inputs, enabling structured understanding,…
LAG: Logic-Augmented Generation from a Cartesian Perspective
Yilin Xiao, Chuang Zhou, Yujing Zhang +5
Large language models (LLMs) have demonstrated remarkable capabilities across a wide range of tasks, yet exhibit critical limitations in knowledge-intensive tasks, often generating…
Why Regression? Binary Encoding Classification Brings Confidence to Stock Market Index Price Prediction
Junzhe Jiang, Chang Yang, Xinrun Wang +1
Stock market indices serve as fundamental market measurement that quantify systematic market dynamics. However, accurate index price prediction remains challenging, primarily becau…
FinMaster: A Holistic Benchmark for Mastering Full-Pipeline Financial Workflows with LLMs
Junzhe Jiang, Chang Yang, Aixin Cui +6
Financial tasks are pivotal to global economic stability; however, their execution faces challenges including labor intensive processes, low error tolerance, data fragmentation, an…
Resolving Latency and Inventory Risk in Market Making with Reinforcement Learning
Junzhe Jiang, Chang Yang, Xinrun Wang +3
The latency of the exchanges in Market Making (MM) is inevitable due to hardware limitations, system processing times, delays in receiving data from exchanges, the time required fo…
Nondeterministic Polynomial-time Problem Challenge: An Ever-Scaling Reasoning Benchmark for LLMs
Chang Yang, Ruiyu Wang, Junzhe Jiang +9
Reasoning is the fundamental capability of large language models (LLMs). Due to the rapid progress of LLMs, there are two main issues of current benchmarks: i) these benchmarks can…
Each Graph is a New Language: Graph Learning with LLMs
Huachi Zhou, Jiahe Du, Chuang Zhou +4
Recent efforts leverage Large Language Models (LLMs) for modeling text-attributed graph structures in node classification tasks. These approaches describe graph structures for LLMs…
LLM-Based World Models Can Make Decisions Solely, But Rigorous Evaluations are Needed
Chang Yang, Xinrun Wang, Junzhe Jiang +2
World model emerges as a key module in decision making, where MuZero and Dreamer achieve remarkable successes in complex tasks. Recent work leverages Large Language Models (LLMs) a…
In-Context Exploiter for Extensive-Form Games
Shuxin Li, Chang Yang, Youzhi Zhang +5
Nash equilibrium (NE) is a widely adopted solution concept in game theory due to its stability property. However, we observe that the NE strategy might not always yield the best re…
Balanced Edge Pruning for Graph Anomaly Detection with Noisy Labels
Zhu Wang, Junnan Dong, Shuang Zhou +3
Graph anomaly detection (GAD) is widely applied in many areas, such as financial fraud detection and social spammer detection. Anomalous nodes in the graph not only impact their ow…
Configurable Mirror Descent: Towards a Unification of Decision Making
Pengdeng Li, Shuxin Li, Chang Yang +5
Decision-making problems, categorized as single-agent, e.g., Atari, cooperative multi-agent, e.g., Hanabi, competitive multi-agent, e.g., Hold'em poker, and mixed cooperative and c…
Reinforcement Nash Equilibrium Solver
Xinrun Wang, Chang Yang, Shuxin Li +4
Nash Equilibrium (NE) is the canonical solution concept of game theory, which provides an elegant tool to understand the rationalities. Though mixed strategy NE exists in any game…
Self-adaptive PSRO: Towards an Automatic Population-based Game Solver
Pengdeng Li, Shuxin Li, Chang Yang +4
Policy-Space Response Oracles (PSRO) as a general algorithmic framework has achieved state-of-the-art performance in learning equilibrium policies of two-player zero-sum games. How…
A Unified Perspective on Deep Equilibrium Finding
Xinrun Wang, Jakub Cerny, Shuxin Li +4
Extensive-form games provide a versatile framework for modeling interactions of multiple agents subjected to imperfect observations and stochastic events. In recent years, two para…