48 citations · 66 across the 15 of their papers we have counts for
15 papers
Sparse by Command: Task-Conditional Compute Skipping for Multi-Task Inference Accelerators
Afzal Ahmad, Gaoyu Mao, Shoubo Hu +4
Multi-task inference models share a single backbone across diverse tasks, yet execute identical computation regardless of which task is active - wasting energy and cycles on task-i…
ReThinker: Scientific Reasoning by Rethinking with Guided Reflection and Confidence Control
Zhentao Tang, Yuqi Cui, Shixiong Kai +10
Expert-level scientific reasoning remains challenging for large language models, particularly on benchmarks such as Humanity's Last Exam (HLE), where rigid tool pipelines, brittle…
One-Token Rollout: Guiding Supervised Fine-Tuning of LLMs with Policy Gradient
Rui Ming, Haoyuan Wu, Shoubo Hu +2
Supervised fine-tuning (SFT) is the predominant method for adapting large language models (LLMs), yet it often struggles with generalization compared to reinforcement learning (RL)…
GHPO: Adaptive Guidance for Stable and Efficient LLM Reinforcement Learning
Ziru Liu, Cheng Gong, Xinyu Fu +7
Reinforcement Learning with Verifiable Rewards (RLVR) has recently emerged as a powerful paradigm for facilitating the self-improvement of large language models (LLMs), particularl…
A Systematic Evaluation of On-Device LLMs: Quantization, Performance, and Resources
Qingyu Song, Rui Liu, Wei Lin +11
Deploying Large Language Models (LLMs) on edge devices enhances privacy but faces performance hurdles due to limited resources. We introduce a systematic methodology to evaluate on…
ToTRL: Unlock LLM Tree-of-Thoughts Reasoning Potential through Puzzles Solving
Haoyuan Wu, Xueyi Chen, Rui Ming +4
Large language models (LLMs) demonstrate significant reasoning capabilities, particularly through long chain-of-thought (CoT) processes, which can be elicited by reinforcement lear…
TorchResist: Open-Source Differentiable Resist Simulator
Zixiao Wang, Jieya Zhou, Su Zheng +5
Recent decades have witnessed remarkable advancements in artificial intelligence (AI), including large language models (LLMs), image and video generative models, and embodied AI sy…
Architect of the Bits World: Masked Autoregressive Modeling for Circuit Generation Guided by Truth Table
Haoyuan Wu, Haisheng Zheng, Shoubo Hu +2
Logic synthesis, a critical stage in electronic design automation (EDA), optimizes gate-level circuits to minimize power consumption and area occupancy in integrated circuits (ICs)…
Efficient Bayesian Optimization with Deep Kernel Learning and Transformer Pre-trained on Multiple Heterogeneous Datasets
Wenlong Lyu, Shoubo Hu, Jie Chuai +1
Bayesian optimization (BO) is widely adopted in black-box optimization problems and it relies on a surrogate model to approximate the black-box response function. With the increasi…
Reframed GES with a Neural Conditional Dependence Measure
Xinwei Shen, Shengyu Zhu, Jiji Zhang +2
In a nonparametric setting, the causal structure is often identifiable only up to Markov equivalence, and for the purpose of causal inference, it is useful to learn a graphical rep…
Contrastive ACE: Domain Generalization Through Alignment of Causal Mechanisms
Yunqi Wang, Furui Liu, Zhitang Chen +4
Domain generalization aims to learn knowledge invariant across different distributions while semantically meaningful for downstream tasks from multiple source domains, to improve t…
A Causal Direction Test for Heterogeneous Populations
Vahid Partovi Nia, Xinlin Li, Masoud Asgharian +3
A probabilistic expert system emulates the decision-making ability of a human expert through a directional graphical model. The first step in building such systems is to understand…
Domain Generalization via Multidomain Discriminant Analysis
Shoubo Hu, Kun Zhang, Zhitang Chen +1
Domain generalization (DG) aims to incorporate knowledge from multiple source domains into a single model that could generalize well on unseen target domains. This problem is ubiqu…
A Kernel Embedding-based Approach for Nonstationary Causal Model Inference
Shoubo Hu, Zhitang Chen, Laiwan Chan
Although nonstationary data are more common in the real world, most existing causal discovery methods do not take nonstationarity into consideration. In this letter, we propose a k…
Causal Inference and Mechanism Clustering of A Mixture of Additive Noise Models
Shoubo Hu, Zhitang Chen, Vahid Partovi Nia +2
The inference of the causal relationship between a pair of observed variables is a fundamental problem in science, and most existing approaches are based on one single causal model…