204 citations · 213 across the 16 of their papers we have counts for
16 papers
Dockerless: Environment-Free Program Verifier for Coding Agents
Wenhao Zeng, Yuling Shi, Xiaodong Gu +10
Program verifiers play a central role in training coding agents, including selecting trajectories for supervised fine-tuning (SFT) and providing rewards for reinforcement learning…
SWE-MeM: Learning Adaptive Memory Management for Long-Horizon Coding Agents
Shuzheng Gao, Wenhao Zeng, Zhaojian Yu +5
Long-horizon software engineering agents often need to manage lengthy and noisy interaction histories under limited context budgets. Existing memory management methods typically re…
GPT Carry-On: Training Foundation Model for Customization Could Be Simple, Scalable and Affordable
Jianqiao Wangni
Modern large language foundation models (LLM) have now entered the daily lives of millions of users. We ask a natural question whether it is possible to customize LLM for every use…
Language Models and Cycle Consistency for Self-Reflective Machine Translation
Jianqiao Wangni
This paper introduces a novel framework that leverages large language models (LLMs) for machine translation (MT). We start with one conjecture: an ideal translation should contain…
Convolutional Networks as Extremely Small Foundation Models: Visual Prompting and Theoretical Perspective
Jianqiao Wangni
Comparing to deep neural networks trained for specific tasks, those foundational deep networks trained on generic datasets such as ImageNet classification, benefits from larger-sca…
Deep Nonparametric Convexified Filtering for Computational Photography, Image Synthesis and Adversarial Defense
Jianqiao Wangni
We aim to provide a general framework of for computational photography that recovers the real scene from imperfect images, via the Deep Nonparametric Convexified Filtering (DNCF).…
Relay Diffusion: Unifying diffusion process across resolutions for image synthesis
Jiayan Teng, Wendi Zheng, Ming Ding +4
Diffusion models achieved great success in image synthesis, but still face challenges in high-resolution generation. Through the lens of discrete cosine transformation, we find the…
Robust Boosting Forests with Richer Deep Feature Hierarchy
Jianqiao Wangni
We propose a robust variant of boosting forest to the various adversarial defense methods, and apply it to enhance the robustness of the deep neural network. We retain the deep net…
Quantized Adaptive Subgradient Algorithms and Their Applications
Ke Xu, Jianqiao Wangni, Yifan Zhang +3
Data explosion and an increase in model size drive the remarkable advances in large-scale machine learning, but also make model training time-consuming and model storage difficult.…
Normalized Diversification
Shaohui Liu, Xiao Zhang, Jianqiao Wangni +1
Generating diverse yet specific data is the goal of the generative adversarial network (GAN), but it suffers from the problem of mode collapse. We introduce the concept of normaliz…
Trajectory Normalized Gradients for Distributed Optimization
Jianqiao Wangni, Ke Li, Jianbo Shi +1
Recently, researchers proposed various low-precision gradient compression, for efficient communication in large-scale distributed optimization. Based on these work, we try to reduc…
Monocular 3D Pose Recovery via Nonconvex Sparsity with Theoretical Analysis
Jianqiao Wangni, Dahua Lin, Ji Liu +2
For recovering 3D object poses from 2D images, a prevalent method is to pre-train an over-complete dictionary of 3D basis poses. During testing, the detect…
Learning Random Fourier Features by Hybrid Constrained Optimization
Jianqiao Wangni, Jingwei Zhuo, Jun Zhu
The kernel embedding algorithm is an important component for adapting kernel methods to large datasets. Since the algorithm consumes a major computation cost in the testing phase,…
Learning Sparse Visual Representations with Leaky Capped Norm Regularizers
Jianqiao Wangni, Dahua Lin
Sparsity inducing regularization is an important part for learning over-complete visual representations. Despite the popularity of regularization, in this paper, we invest…
Gradient Sparsification for Communication-Efficient Distributed Optimization
Jianqiao Wangni, Jialei Wang, Ji Liu +1
Modern large scale machine learning applications require stochastic optimization algorithms to be implemented on distributed computational architectures. A key bottleneck is the co…
Training L1-Regularized Models with Orthant-Wise Passive Descent Algorithms
Jianqiao Wangni
The -regularized models are widely used for sparse regression or classification tasks. In this paper, we propose the orthant-wise passive descent algorithm (OPDA) for optimizi…