# Paper-List

| Date | Paper | Presenter | Note |
|:------------:|:-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------:|:-------------:| -------------------------------------------------------------------------------------------------------------- |
| Apr 10 | | Yujian Liu | |
| Apr 3 | Clean backdoor attack by guided diffusion | Yuguang Yao | |
| Mar 20 | embedding dim exposed | Qiucheng Wu | |
| Mar 13 | | Yihua Zhang | |
| Feb 14, 2024 | Data Selection for LLM via Influence from Danqi Group | Yujian Liu | |
| Feb 7, 2024 | Geographically bias in LLM | Jinghan Jia | |
| Jan 17 | Mistral | Jiabao Ji | |
| Jan 10 | | Yimeng Zhang | |
| Dec 19 | | Bairu Hou | |
| Dec 5 | Large Vision Model | Yuguang Yao | |
| Nov 29 | Scalable extraction from LLM | Qiucheng Wu | |
| Nov 8 | Diffusion model related paper | Yihua | |
| Oct 25 | | Yujian | |
| | | Jinghan | |
| Sep 13 | Certifying LLM safety against adversarial prompting | Bairu Hou | |
| Sep 6 | Denfense against adv attack against LLM | Qiucheng Wu | |
| Aug 30 | Maybe Only 0.5% Data is Needed: A Preliminary Exploration of Low Training Data Instruction Tuning | Yimeng Zhang | |
| Aug 16 | [Tree-Ring Watermarks: Fingerprints for Diffusion Images that are Invisible and Robust](https://arxiv.org/pdf/2305.20030.pdf) | Jiabao Ji | |
| Aug 2 | [Diffusion Classifier](https://arxiv.org/pdf/2303.16203.pdf) | Yuguang Yao | |
| July 12 | [BLIP-2](https://arxiv.org/abs/2301.12597) | Bairu Hou | The bridge between image encoder and an LLM |
| July 5 | [Can Forward Gradient Match Backpropagation?](https://arxiv.org/abs/2306.06968) | Aochuan Chen | |
| April 26 | | Yujian Liu | |
| Apr 19 | Diffusion Models | Yihua Zhang | |
| | [ In-context Example Selection with Influences](https://arxiv.org/pdf/2302.11042v1.pdf) | Jiabao Ji | |
| | VISUAL CLASSIFICATION VIA DESCRIPTION FROM LARGE LANGUAGE MODELS. | Jinghan Jia | |
| | | Qiucheng Wu | |
| | | Yimeng Zhang | |
| Feb 22 | https://arxiv.org/pdf/2302.03668.pdf | Bairu Hou | Prompt Tuning |
| Feb 15 | | Yuguang Yao | |
| Feb 1 | | Yujian Liu | |
| Jan 11 | Estimating Gradients of the data distribution | Aochuan Chen | Scorebased |
| Nov 23 | Indicators of Attack Failure: Debugging and Improving Optimization of Adversarial Examples | Yihua Zhang | |
| Nov 2 2022 | Fair Infinitesimal Jackknife: Mitigating the Influence of Biased Training Data Points Without Refitting | Jinghan Jia | [Slides](https://docs.google.com/presentation/d/1zuEpfZI2f17AyLmwKJfCqTbg6ffhKX1Bj3Q6TXmKdK4/edit) |
| Oct 26 | Cold Diffusion: Inverting Arbitrary Image Transforms Without Noise | Jiabao Ji | |
| Oct 19 | Untargeted Backdoor Watermark: Towards Harmless and Stealthy Dataset Copyright Protection | Bairu Hou | |
| Oct 12 | Diffusion Models for Adversarial Purification ([ICML 2022]) | Qiucheng Wu | |
| Oct 5 | Test-Time Prompt Tuning for Zero-Shot Generalization in Vision-Language Models | Yimeng Zhang | |
| Sep 13 | two papers on improving adversarial robustness with information bottleneck in NLP | Guanhua | [Slides](https://www.overleaf.com/read/bwhqrjzpyxhx) |
| Aug 29 | [Label-Free Explainability for Unsupervised Models](https://proceedings.mlr.press/v162/crabbe22a/crabbe22a.pdf) | Yuguang Yao | [Slides](https://docs.google.com/presentation/d/1HoIp4cY25KoPPjoiUBNEKpo9h73F3WA1QC9Vr6bjI88/edit?usp=sharing) |
| Aug 23 | [Loss Function Learning for Domain Generalization by Implicit Gradient](https://proceedings.mlr.press/v162/gao22b/gao22b.pdf) | Aochuan Chen | |
| July 5 | [Subspace Adversarial Training](https://arxiv.org/pdf/2111.12229.pdf) | Yihua Zhang | |
| June 28 | [NeRF]( https://dl.acm.org/doi/pdf/10.1145/3503250NeRF ) | Qiucheng Wu | |
| June 14 | [Towards Reverse-Engineering Black-Box Neural Networks](https://arxiv.org/abs/1711.01768) | Yuguang Yao | |
| June 7 | [Learning Neural Network Subspaces](https://arxiv.org/pdf/2102.10472.pdf) | Yihua Zhang | |
| May 3 | [ON ROBUST PREFIX-TUNING FOR TEXT CLASSIFICATION](https://openreview.net/pdf?id=eBCmOocUejf) | Bairu Hou | |
| April26 | [Coarsening the Granularity: Towards Structurally Sparse Lottery Tickets](https://arxiv.org/abs/2202.04736) | Yuguang Yao | |
| April19 | [Connect, Not Collapse: Explaining Contrastive Learning for Unsupervised Domain Adaptation](https://arxiv.org/pdf/2204.00570v1.pdf) | Jinghan Jia | |
| April12 | [WARP: Word-level Adversarial ReProgramming ](https://arxiv.org/pdf/2101.00121.pdf) | Guanhua Zhang | |
| March29 | [HOW MANY DEGREES OF FREEDOM DO WE NEED TO TRAIN DEEP NETWORKS: A LOSS LANDSCAPE PERSPECTIVE](https://openreview.net/pdf?id=ChMLTGRjFcU) | Yihua Zhang | |
| March22 | [Understanding Black-box Predictions via Influence Functions](https://arxiv.org/pdf/1703.04730.pdf) | Qiucheng Wu | |
| March15 | [Mixed-Privacy Forgetting in Deep Networks](https://openaccess.thecvf.com/content/CVPR2021/papers/Golatkar_Mixed-Privacy_Forgetting_in_Deep_Networks_CVPR_2021_paper.pdf) | Qiucheng Wu | |
| March1 | [Gradients without Backpropagation](https://arxiv.org/pdf/2202.08587.pdf) | Jinghan Jia | |
| Feb22 | [BADPRE: TASK-AGNOSTIC BACKDOOR ATTACKS TO PRE-TRAINED NLP FOUNDATION MODELS](https://openreview.net/pdf?id=Mng8CQ9eBW) | Bairu Hou | |
| Feb22 | [FIXED NEURAL NETWORK STEGANOGRAPHY: TRAIN THE IMAGES, NOT THE NETWORK ](https://openreview.net/forum?id=hcMvApxGSzZ) | Yuguang Yao | [Slides](https://docs.google.com/presentation/d/1VFaRsOEUmXe1Fr2uXnIBrerCJUFDgI5cUNljS8vkFsU/edit?usp=sharing) |
| Feb15 | [Multiaccuracy: Black-Box Post-Processing for Fairness in Classification ](https://arxiv.org/abs/1805.12317) | Guanhua Zhang | |
| Feb8 2022 | [Neural Manifold Cluster and Embed](https://arxiv.org/pdf/2201.10000.pdf) | Zichen Chen | [Code](https://github.com/zengyi-li/NMCE-release) |
| Jan25 2022 | [FFCV](https://github.com/libffcv/ffcv) | Yuguang Yao | [Slides](https://yuguang-yao.slides.com/yaoyugua/deck-5cb81c/fullscreen?token=y9VF9g5A) |
| Jan11 2022 | [Phrase-level Adversarial Example Generation for Neural Machine Translation](https://arxiv.org/pdf/2201.02009.pdf) | Bairu Hou | |
| Jan4 2022 | [Adversarial Reprogramming of Neural Networks](https://arxiv.org/abs/1806.11146) | Yihua Zhang | |
| Dec21 2021 | [Combining Diverse Feature Priors](https://arxiv.org/abs/2110.08220) | Jinghan Jia | |
| Dec14 2021 | [Certified Patch Robustness via Smoothed Vision Transformers](https://arxiv.org/abs/2110.07719) | Yuguang Yao | [Slides](https://yuguang-yao.slides.com/yaoyugua/deck/fullscreen?token=0aiZnAQJ) |
| Nov30 2021 | [SpAtten: Efficient Sparse Attention Architecture with Cascade Token and Head Pruning](https://arxiv.org/abs/2012.09852) | Qiucheng Wu | |
| Nov23 2021 | [MetNet-2: Deep Learning for 12-Hour Precipitation Forecasting](https://arxiv.org/pdf/2111.07470.pdf) | Yimeng Zhang | |
| Nov9 2021 | [VQ-GNN: A Universal Framework to Scale-up Graph Neural Networks using Vector Quantization](https://arxiv.org/pdf/2110.14363.pdf) | Bairu Hou | |
| Oct26 2021 | [VATT: Transformers for Multimodal Self-Supervised Learning from Raw Video, Audio and Text](https://arxiv.org/pdf/2104.11178.pdf) | Jinghan Jia | [Slides](https://www.overleaf.com/project/6176f1d3cfe1a9852e70f661) |
| Oct19 2021 | [1. Decoupled contrastive learning;](https://arxiv.org/pdf/2110.06848.pdf) [2. SALIENT IMAGENET: HOW TO DISCOVER SPURIOUS FEATURES IN DEEP LEARNING.](https://arxiv.org/pdf/2110.04301.pdf) | Guanhua Zhang | |
| Oct12 2021 | [1. TOWARDS FAST AND EFFECTIVE SINGLE-STEP ADVERSARIAL TRAINING;](https://openreview.net/pdf?id=fRnRsdc_nR7) [2. TOWARDS UNDERSTANDING CATASTROPHIC OVERFITTING IN FAST ADVERSARIAL TRAINING.](https://openreview.net/pdf?id=lDvJM5XUyrx) | Yihua Zhang | [Slides](https://www.overleaf.com/read/zmtbpzfnvrcn) |
| Sep21 2021 | Bairu Hou | | |
| Sep14 2021 | Yimeng Zhang | | |
| Sep14 2021 | Guanhua Zhang | | [Slides]( https://www.overleaf.com/read/crjssxhkkhkt) |
| Sep7 2021 | | | |
| Sep2 2021 | | | |