You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Revise Projects section to include new research initiatives and enhance organization
- Replaced the existing Key Projects section with a more detailed overview of Large Language Models & AI Safety, Federated Learning & Privacy, and GPU-Accelerated Machine Learning.
- Added new projects with corresponding paper titles, venues, descriptions, and links for better accessibility and information dissemination.
- Improved formatting for clarity and consistency across project entries.
Copy file name to clipboardExpand all lines: about/projects.md
+58-9Lines changed: 58 additions & 9 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -4,12 +4,61 @@ sidebar_position: 2
4
4
5
5
# Projects
6
6
7
-
## Key Projects
8
-
9
-
| Project | Venue | Description |
10
-
|---------|-------|-------------|
11
-
|[LLM-PBE](https://github.com/Xtra-Computing/LLM-PBE)| SIGMOD 2024 *(Best Paper Nomination)*| Toolkit for systematic evaluation of data privacy risks in LLMs |
12
-
|[VertiBench](https://github.com/Xtra-Computing/VertiBench)| ICLR 2024 | Benchmarks for vertical federated learning with diverse feature distributions |
|[LLM-DNA](https://github.com/Xtra-Computing/LLM-DNA)<br/>| LLM DNA: Tracing Model Evolution via Functional Representations | ICLR 2026 *(Oral)*| Training-free framework for tracing LLM evolution via functional representations |[Paper](https://openreview.net/forum?id=UIxHaAqFqQ)[Website](https://dna.xtra.science/)|
12
+
|[LLM-Deception](https://github.com/Xtra-Computing/LLM-Deception)<br/>| Beyond Prompt-Induced Lies: Investigating LLM Deception on Benign Prompts | ICLR 2026 *(Oral)*| Investigating LLM deceptive behavior on benign prompts using graph connectivity problems |[arXiv](https://arxiv.org/abs/2508.06361)|
13
+
|[DGP](https://github.com/Xtra-Computing/DGP)<br/>| DGP: A Dual-Granularity Prompting Framework for Fraud Detection with Graph-Enhanced LLMs | AAAI 2026 | Dual-Granularity Prompting Framework for fraud detection with graph-enhanced LLMs |[arXiv](https://arxiv.org/abs/2507.21653)|
14
+
|[Llamdex](https://github.com/Xtra-Computing/Llamdex)<br/>| Model-based Large Language Model Customization as Service | EMNLP 2025 Main | Model-based LLM customization service - upload models instead of data |[Paper](https://aclanthology.org/2025.emnlp-main.248.pdf)|
15
+
|[MegaAgent](https://github.com/Xtra-Computing/MegaAgent)<br/>| MegaAgent: A Large-Scale Autonomous LLM-based Multi-Agent System Without Predefined SOPs | ACL 2025 Findings | Large-scale autonomous LLM-based multi-agent system with dynamic task decomposition |[arXiv](https://arxiv.org/abs/2408.09955)[ACL](https://aclanthology.org/2025.findings-acl.259/)|
16
+
|[CryptoTrade](https://github.com/Xtra-Computing/CryptoTrade)<br/>| CryptoTrade: A Reflective LLM-based Agent to Guide Zero-shot Cryptocurrency Trading | EMNLP 2024 | Reflective LLM-based agent for cryptocurrency trading with on-chain and off-chain data analysis |[Paper](https://aclanthology.org/2024.emnlp-main.63.pdf)|
17
+
18
+
## Federated Learning & Privacy
19
+
20
+
| Project | Paper Title | Venue | Description | Links |
|[FeT](https://github.com/Xtra-Computing/FeT)<br/>| Federated Transformer: Multi-Party Vertical Federated Learning on Practical Fuzzily Linked Data | NeurIPS 2024 | Multi-party VFL framework for fuzzy identifiers (46% accuracy improvement at 50 parties) |[arXiv](https://arxiv.org/abs/2410.17986)|
23
+
|[LLM-PBE](https://github.com/QinbinLi/LLM-PBE)<br/>| LLM-PBE: Assessing Data Privacy in Large Language Models | SIGMOD 2024 *(Best Paper Nomination)*| Toolkit for systematic evaluation of data privacy risks in LLMs |[Website](https://llm-pbe.github.io/home)|
24
+
|[VertiBench](https://github.com/Xtra-Computing/VertiBench)<br/>| VertiBench: Advancing Feature Distribution Diversity in Vertical Federated Learning Benchmarks | ICLR 2024 | Benchmark for vertical federated learning with diverse feature distributions and imbalance |[arXiv](https://arxiv.org/abs/2307.02040)[Website](https://vertibench.xtra.science/)|
25
+
|[ModelGo](https://github.com/Xtra-Computing/ModelGo)<br/>| ModelGo: A Practical Tool for Machine Learning License Analysis | WWW 2024 *(Oral)*| License analysis tool for machine learning projects with ML-specific licensing framework | - |
26
+
|[FedTree](https://github.com/Xtra-Computing/FedTree)<br/>| FedTree: A Federated Learning System For Trees | MLSys 2023 | Federated learning system for tree-based models with HE, secure aggregation, and DP |[Docs](https://fedtree.readthedocs.io/)|
|[FedSim](https://github.com/Xtra-Computing/FedSim)<br/>| A Coupled Design of Exploiting Record Similarity for Practical Vertical Federated Learning | NeurIPS 2022 | Coupled VFL framework leveraging record similarities for improved performance | - |
30
+
|[NIID-Bench](https://github.com/Xtra-Computing/NIID-Bench)<br/>| Federated Learning on Non-IID Data Silos: An Experimental Study | ICDE 2022 | Comprehensive FL benchmark for non-IID data with 4 algorithms and 9 datasets | - |
31
+
32
+
## GPU-Accelerated Machine Learning
33
+
34
+
| Project | Paper Title | Venue | Description | Links |
|[DeltaBoost](https://github.com/Xtra-Computing/DeltaBoost)<br/>| DeltaBoost: Gradient Boosting Decision Trees with Efficient Machine Unlearning | SIGMOD 2023 *(Honorable Mention for Best Artifact Award)*| GBDT-based model with efficient machine unlearning capability | - |
37
+
|[ThunderSVM](https://github.com/Xtra-Computing/thundersvm)<br/>| ThunderSVM: A Fast SVM Library on GPUs and CPUs | JMLR 2018 | Fast SVM library on GPUs and CPUs with scikit-learn interface |[Docs](https://thundersvm.readthedocs.io/)|
38
+
|[ThunderGBM](https://github.com/Xtra-Computing/thundergbm)<br/>| Exploiting GPUs for Efficient Gradient Boosting Decision Tree Training | IEEE TPDS 2019 *(Best Paper)*, JMLR 2020 | Fast gradient boosted trees and random forests on GPUs (10x speedup) |[Docs](https://thundergbm.readthedocs.io/)|
39
+
40
+
## Graph Processing Systems
41
+
42
+
| Project | Paper Title | Venue | Description | Links |
|[RidgeWalker](https://github.com/Xtra-Computing/RidgeWalker)<br/>| RidgeWalker: Perfectly Pipelined Graph Random Walks on FPGAs | HPCA 2026 | FPGA accelerator for graph random walks with zero-bubble scheduler | - |
45
+
|[Clementi](https://github.com/Xtra-Computing/Clementi)<br/>| Clementi: Efficient Load Balancing and Communication Overlap for Multi-FPGA Graph Processing | SIGMOD 2025 | Multi-FPGA graph processing framework with near-linear scalability (1.86-8.75x speedup) | - |
46
+
|[RUSH](https://github.com/Xtra-Computing/RUSH)<br/>| RUSH: Real-time Burst Subgraph Detection in Dynamic Graphs | VLDB 2024 | Real-time fraud detection framework for dynamic graphs with burst subgraph discovery |[Paper](https://www.vldb.org/pvldb/vol17/p3657-chen.pdf)|
47
+
|[ThunderGP](https://github.com/Xtra-Computing/ThunderGP)<br/>| ThunderGP: Resource-Efficient Graph Processing Framework on FPGAs with HLS | ACM TRETS 2022 *(Best Papers in FPGA 2021)*, FPGA 2021 | HLS-based graph processing framework on FPGAs (fastest on HLS-based FPGAs) | - |
48
+
|[G3](https://github.com/Xtra-Computing/G3)<br/>| G3: When Graph Neural Networks Meet Parallel Graph Processing Systems on GPUs | VLDB 2020 Demo | Programmable GNN training system on GPU with graph-centric optimizations |[Demo](https://g3-gui.web.app/)[Video](https://www.youtube.com/watch?v=UJH0nh38wSg)|
|[OEBench](https://github.com/Xtra-Computing/OEBench)<br/>| OEBench: Investigating Open Environment Challenges in Real-World Relational Data Streams | VLDB 2024 | Benchmark for open environment challenges in relational data streams (55 datasets) | - |
57
+
|[BriskStream](https://github.com/Xtra-Computing/briskstream)<br/>| BriskStream: Scaling Stream Processing on Multicore Architectures | SIGMOD 2019 | Multicore, NUMA-optimized data stream processing system |[arXiv](https://arxiv.org/abs/1904.03800)|
58
+
|[PyOE](https://github.com/Xtra-Computing/PyOE)<br/>| PyOE: Python Library for Data Stream Learning | - | Machine learning library for data stream learning with 6 tasks support |[Website](https://pyoe.xtra.science/home)|
59
+
60
+
## Hardware Acceleration & Optimization
61
+
62
+
| Project | Paper Title | Venue | Description | Links |
|[HIPACK](https://github.com/Xtra-Computing/HIPACK)<br/>| HiPACK: Efficient Sub-8-Bit Direct Convolution with SIMD and Bitwise Management | MICRO 2025 | Sub-8-bit direct convolution acceleration for ARM processors (3.2x+ speedup) | - |
0 commit comments