1.8k citations · 3.8k across the 131 of their papers we have counts for
19 papers · 1 filter
APPO: Agentic Procedural Policy Optimization
Xucong Wang, Ziyu Ma, Yong Wang +5
Recent advances in agentic Reinforcement Learning (RL) have substantially improved the multi-turn tool-use capabilities of large language model agents. However, most existing metho…
Ranking-aware Reinforcement Learning for Ordinal Ranking
Aiming Hao, Chen Zhu, Jiashu Zhu +2
Ordinal regression and ranking are challenging due to inherent ordinal dependencies that conventional methods struggle to model. We propose Ranking-Aware Reinforcement Learning (RA…
AdaCuRL: Adaptive Curriculum Reinforcement Learning with Invalid Sample Mitigation and Historical Revisiting
Renda Li, Hailang Huang, Fei Wei +3
Reinforcement learning (RL) has demonstrated considerable potential for enhancing reasoning in large language models (LLMs). However, existing methods suffer from Gradient Starvati…
Tree Search for LLM Agent Reinforcement Learning
Yuxiang Ji, Ziyu Ma, Yong Wang +3
Recent advances in reinforcement learning (RL) have significantly enhanced the agentic capabilities of large language models (LLMs). In long-term and multi-turn agent tasks, existi…
Effective Probabilistic Time Series Forecasting with Fourier Adaptive Noise-Separated Diffusion
Xinyan Wang, Rui Dai, Kaikui Liu +1
We propose the Fourier Adaptive Lite Diffusion Architecture (FALDA), a novel probabilistic framework for time series forecasting. First, we introduce the Diffusion Model for Residu…
GPG: A Simple and Strong Reinforcement Learning Baseline for Model Reasoning
Xiangxiang Chu, Hailang Huang, Xiao Zhang +2
Reinforcement Learning (RL) can directly enhance the reasoning capabilities of large language models without extensive reliance on Supervised Fine-Tuning (SFT). In this work, we re…
A Speed Odyssey for Deployable Quantization of LLMs
Qingyuan Li, Ran Meng, Yiduo Li +6
The large language model era urges faster and less costly inference. Prior model compression works on LLMs tend to undertake a software-centric approach primarily focused on the si…
Robust MAE-Driven NAS: From Mask Reconstruction to Architecture Innovation
Yiming Hu, Xiangxiang Chu, Yong Wang
Neural Architecture Search (NAS) relies heavily on labeled data, which is labor-intensive and time-consuming to obtain. In this paper, we propose a novel NAS method based on an uns…
Norm Tweaking: High-performance Low-bit Quantization of Large Language Models
Liang Li, Qingyuan Li, Bo Zhang +1
As the size of large language models (LLMs) continues to grow, model compression without sacrificing accuracy has become a crucial challenge for deployment. While some quantization…
DAAS: Differentiable Architecture and Augmentation Policy Search
Xiaoxing Wang, Xiangxiang Chu, Junchi Yan +1
Neural architecture search (NAS) has been an active direction of automatic machine learning (Auto-ML), aiming to explore efficient network structures. The searched architecture is…
ROME: Robustifying Memory-Efficient NAS via Topology Disentanglement and Gradient Accumulation
Xiaoxing Wang, Xiangxiang Chu, Yuda Fan +4
Albeit being a prevalent architecture searching approach, differentiable architecture search (DARTS) is largely hindered by its substantial memory cost since the entire supernet re…
DARTS-: Robustly Stepping out of Performance Collapse Without Indicators
Xiangxiang Chu, Xiaoxing Wang, Bo Zhang +3
Despite the fast development of differentiable architecture search (DARTS), it suffers from long-standing performance instability, which extremely limits its application. Existing…
Noisy Differentiable Architecture Search
Xiangxiang Chu, Bo Zhang
Simplicity is the ultimate sophistication. Differentiable Architecture Search (DARTS) has now become one of the mainstream paradigms of neural architecture search. However, it larg…
MixPath: A Unified Approach for One-shot Neural Architecture Search
Xiangxiang Chu, Shun Lu, Xudong Li +1
Blending multiple convolutional kernels is proved advantageous in neural architecture design. However, current two-stage neural architecture search methods are mainly limited to si…
Fair DARTS: Eliminating Unfair Advantages in Differentiable Architecture Search
Xiangxiang Chu, Tianbao Zhou, Bo Zhang +1
Differentiable Architecture Search (DARTS) is now a widely disseminated weight-sharing neural architecture search method. However, it suffers from well-known performance collapse d…
SCARLET-NAS: Bridging the Gap between Stability and Scalability in Weight-sharing Neural Architecture Search
Xiangxiang Chu, Bo Zhang, Qingyuan Li +2
To discover powerful yet compact models is an important goal of neural architecture search. Previous two-stage one-shot approaches are limited by search space with a fixed depth. I…
MoGA: Searching Beyond MobileNetV3
Xiangxiang Chu, Bo Zhang, Ruijun Xu
The evolution of MobileNets has laid a solid foundation for neural network applications on mobile end. With the latest MobileNetV3, neural architecture search again claimed its sup…
FairNAS: Rethinking Evaluation Fairness of Weight Sharing Neural Architecture Search
Xiangxiang Chu, Bo Zhang, Ruijun Xu
One of the most critical problems in weight-sharing neural architecture search is the evaluation of candidate models within a predefined search space. In practice, a one-shot super…
Policy Optimization With Penalized Point Probability Distance: An Alternative To Proximal Policy Optimization
Xiangxiang Chu
As the most successful variant and improvement for Trust Region Policy Optimization (TRPO), proximal policy optimization (PPO) has been widely applied across various domains with s…