27 citations · 33 across the 18 of their papers we have counts for
22 papers
Terrarium: Growing Personal Assistants via Scalable Synthesis of App Worlds
Mengzhou Wu, Yuzhe Guo, Jiawen Tao +9
Advances in large language models (LLMs) have brought the vision of a general-purpose personal assistant closer to reality. Such assistants could provide a unified natural-language…
TileCas: Cascading Kernel Development Across Programming Abstractions
Xinyu Xiao, Zihe Song, Dezhi Ran +2
Programming abstractions have traditionally been designed for humans, but code generation is increasingly performed by models and autonomous agents. We investigate abstractions for…
Beyond Accuracy: Prefix-Invariant Realizations of Low-Precision Fast Matrix Multiplication
Shuxiao Xie, Shuyang Xie, Yuan Cao +3
Fast matrix multiplication saves multiplications through exact cancellation, but rounding sums that mix token rows can leave contributions from later tokens in earlier language mod…
Backward-State Policy Is Part of the Learning Algorithm
Shuxiao Xie, Shuyang Xie, Dezhi Ran +2
Low-precision training rounds tensors that the backward pass reads again, often for several gradients; each use can read the forward's rounded value, the original, or a new random…
Fast Matrix Multiplication in fp8: Certified Coefficient Optimization and Measured Error
Shuxiao Xie, Shuyang Xie, Yuan Cao +3
A Strassen-type algorithm has many realizations with the same exact product and multiplication count yet different fp8 error because basis changes reshape coefficient geometry, pos…
One QK Channel, Many Sources: Tracing Low-Precision Attention Collapse
Shuxiao Xie, Shuyang Xie, Yuan Cao +3
A bfloat16 transformer can train normally, then collapse abruptly. Prior work links collapse to structured attention errors and shows QK normalization disrupts their compounding. D…
BackendForge: Benchmarking Agentic End-to-End Code Generation with Backend Services
Yuzhe Guo, Mengzhou Wu, Yuan Cao +4
Large language models (LLMs) are increasingly used in agentic coding settings, where they can inspect files, execute commands, run tests, observe failures, and iteratively revise c…
UI-Oceanus: Scaling GUI Agents with Synthetic Environmental Dynamics
Mengzhou Wu, Yuzhe Guo, Yuan Cao +16
Scaling generalist GUI agents is hindered by the data scalability bottleneck of expensive human demonstrations and the "distillation ceiling" of synthetic teacher supervision. To t…
An Empirical Study and Theoretical Explanation on Task-Level Model-Merging Collapse
Yuan Cao, Dezhi Ran, Yuzhe Guo +5
Model merging unifies independently fine-tuned LLMs from the same base, enabling reuse and integration of parallel development efforts without retraining. However, in practice we o…
GUI-GENESIS: Automated Synthesis of Efficient Environments with Verifiable Rewards for GUI Agent Post-Training
Yuan Cao, Dezhi Ran, Mengzhou Wu +9
Post-training GUI agents in interactive environments is critical for developing generalization and long-horizon planning capabilities. However, training on real-world applications…
From User Interface to Agent Interface: Efficiency Optimization of UI Representations for LLM Agents
Dezhi Ran, Zhi Gong, Yuzhe Guo +10
While Large Language Model (LLM) agents show great potential for automated UI navigation such as automated UI testing and AI assistants, their efficiency has been largely overlooke…
KernelBand: Steering LLM-based Kernel Optimization via Hardware-Aware Multi-Armed Bandits
Dezhi Ran, Shuxiao Xie, Mingfang Ji +9
High-performance GPU kernels are critical for efficient LLM serving, yet their optimization remains a bottleneck requiring deep system expertise. While code LLMs show promise in ge…
AppForge: From Assistant to Independent Developer -- Are GPTs Ready for Software Development?
Dezhi Ran, Yuan Cao, Mengzhou Wu +10
Large language models (LLMs) have demonstrated remarkable capability in function-level code generation tasks. Unlike isolated functions, real-world applications demand reasoning ov…
Beyond Pass or Fail: Multi-Dimensional Benchmarking of Foundation Models for Goal-based Mobile UI Navigation
Dezhi Ran, Mengzhou Wu, Hao Yu +15
Recent advances of foundation models (FMs) have made navigating mobile applications (apps) based on high-level goal instructions within reach, with significant industrial applicati…
Recent Advances in Large Langauge Model Benchmarks against Data Contamination: From Static to Dynamic Evaluation
Simin Chen, Yiming Chen, Zexin Li +8
Data contamination has received increasing attention in the era of large language models (LLMs) due to their reliance on vast Internet-derived training corpora. To mitigate the ris…
Data and System Perspectives of Sustainable Artificial Intelligence
Tao Xie, David Harel, Dezhi Ran +11
Sustainable AI is a subfield of AI for concerning developing and using AI systems in ways of aiming to reduce environmental impact and achieve sustainability. Sustainable AI is inc…
DeCon: Detecting Incorrect Assertions via Postconditions Generated by a Large Language Model
Hao Yu, Tianyu Chen, Jiaming Huang +8
Recently, given the docstring for the target problem and the target function signature, large language models (LLMs) have been used not only to generate source code, but also to ge…
An Infrastructure Software Perspective Toward Computation Offloading between Executable Specifications and Foundation Models
Dezhi Ran, Mengzhou Wu, Yuan Cao +3
Foundation Models (FMs) have become essential components in modern software systems, excelling in tasks such as pattern recognition and unstructured data processing. However, their…
Skill-Adaptive Imitation Learning for UI Test Reuse
Mengzhou Wu, Hao Wang, Jun Ren +7
To alleviate the substantial cost of manually crafting user interface (UI) test cases, UI test migration aims to automatically generate test cases for a target mobile application (…
SWE-bench-java: A GitHub Issue Resolving Benchmark for Java
Daoguang Zan, Zhirong Huang, Ailun Yu +17
GitHub issue resolving is a critical task in software engineering, recently gaining significant attention in both industry and academia. Within this task, SWE-bench has been releas…
Foundation Model Engineering: Engineering Foundation Models Just as Engineering Software
Dezhi Ran, Mengzhou Wu, Wei Yang +1
By treating data and models as the source code, Foundation Models (FMs) become a new type of software. Mirroring the concept of software crisis, the increasing complexity of FMs ma…
CoderEval: A Benchmark of Pragmatic Code Generation with Generative Pre-trained Models
Hao Yu, Bo Shen, Dezhi Ran +7
Code generation models based on the pre-training and fine-tuning paradigm have been increasingly attempted by both academia and industry, resulting in well-known industrial models…