7 citations · 16 across the 21 of their papers we have counts for
26 papers
Federation over Harness
Dixi Yao, Tahseen Rabbani, Tian Li
Modern LLM-powered agents increasingly improve through experience sharing, where distributed agents distill local reasoning experience into reusable knowledge, such as a shared ins…
Private Retrieval Augmented Generation via Random Projection
Dixi Yao, Tahseen Rabbani, Tian Li
Retrieval-Augmented Generation (RAG) enhances the capabilities of large language models (LLMs) by querying external structured knowledge. However, it can also introduce privacy ris…
SEIS: Self-Evolving Inference Systems
Zhen Xu, Jingyu Liu, Zongze Li +2
Inference systems determine how fast and how cheaply language models can be served, so making them faster has direct practical value. However, prior work focuses mostly on optimizi…
Persistent Watermarking of Text-to-Image Models
Dixi Yao, Kaiwen Chen, Tahseen Rabbani +1
Text-to-image (T2I) generation is gaining increasing popularity with the general public, motivating the development of reliable mechanisms for copyrighting such models given their…
Federation over Text: Insight Sharing for Multi-Agent Reasoning
Dixi Yao, Tahseen Rabbani, Manzil Zaheer +1
Modern agents specialize in varying domains while there is no clear approach combining different domain skills. We propose a federated learning-like framework, Federation over Text…
Not All Prefills Are Equal: PPD Disaggregation for Multi-turn LLM Serving
Zongze Li, Jingyu Liu, Zhen Xu +3
Prefill-Decode (PD) disaggregation has become the standard architecture for modern LLM inference engines, which alleviates the interference of two distinctive workloads. With the g…
Asynchronous Heavy-Tailed Optimization
Junfei Sun, Dixi Yao, Xuchen Gong +3
Heavy-tailed stochastic gradient noise, commonly observed in transformer models, can destabilize the optimization process. Recent works mainly focus on developing and understanding…
Hold Onto That Thought: Assessing KV Cache Compression On Reasoning
Minghui Liu, Aadi Palnitkar, Tahseen Rabbani +9
Large language models (LLMs) have demonstrated remarkable performance on long-context tasks, but are often bottlenecked by memory constraints. Namely, the KV cache, which is used t…
DISCO: A Browser-Based Privacy-Preserving Framework for Distributed Collaborative Learning
Julien T. T. Vignoud, Valérian Rousset, Hugo El Guedj +28
Data is often impractical to share for a range of well considered reasons, such as concerns over privacy, intellectual property, and legal constraints. This not only fragments the…
PRBench: Large-Scale Expert Rubrics for Evaluating High-Stakes Professional Reasoning
Afra Feyza Akyürek, Advait Gosai, Chen Bo Calvin Zhang +21
Frontier model progress is often measured by academic benchmarks, which offer a limited view of performance in real-world professional contexts. Existing evaluations often fail to…
ResearchRubrics: A Benchmark of Prompts and Rubrics For Evaluating Deep Research Agents
Manasi Sharma, Chen Bo Calvin Zhang, Chaithanya Bandi +13
Deep Research (DR) is an emerging agent application that leverages large language models (LLMs) to address open-ended queries. It requires the integration of several capabilities,…
Remote Labor Index: Measuring AI Automation of Remote Work
Mantas Mazeika, Alice Gatti, Cristina Menghini +44
AIs have made rapid progress on research-oriented benchmarks of knowledge and reasoning, but it remains unclear how these gains translate into economic value and automation. To mea…
Access Paths for Efficient Ordering with Large Language Models
Fuheng Zhao, Jiayue Chen, Yiming Pan +7
In this work, we present the \texttt{LLM ORDER BY} semantic operator as a logical abstraction and conduct a systematic study of its physical implementations. First, we propose seve…
Mitigating Unintended Memorization with LoRA in Federated Learning for LLMs
Thierry Bossy, Julien Vignoud, Tahseen Rabbani +2
Federated learning (FL) is a popular paradigm for collaborative training which avoids direct data exposure between clients. However, data privacy issues still remain: FL-trained la…
HashEvict: A Pre-Attention KV Cache Eviction Strategy using Locality-Sensitive Hashing
Minghui Liu, Tahseen Rabbani, Tony O'Halloran +5
Transformer-based large language models (LLMs) use the key-value (KV) cache to significantly accelerate inference by storing the key and value embeddings of past tokens. However, t…
Balancing Label Imbalance in Federated Environments Using Only Mixup and Artificially-Labeled Noise
Kyle Sang, Tahseen Rabbani, Furong Huang
Clients in a distributed or federated environment will often hold data skewed towards differing subsets of labels. This scenario, referred to as heterogeneous or non-iid federated…
Sketch-GNN: Scalable Graph Neural Networks with Sublinear Training Complexity
Mucong Ding, Tahseen Rabbani, Bang An +2
Graph Neural Networks (GNNs) are widely applied to graph learning problems such as node classification. When scaling up the underlying graphs of GNNs to a larger size, we are force…
Calibrated Dataset Condensation for Faster Hyperparameter Search
Mucong Ding, Yuancheng Xu, Tahseen Rabbani +5
Dataset condensation can be used to reduce the computational cost of training multiple models on a large dataset by condensing the training dataset into a small synthetic set. Stat…
A Linear Time and Space Local Point Cloud Geometry Encoder via Vectorized Kernel Mixture (VecKM)
Dehao Yuan, Cornelia Fermüller, Tahseen Rabbani +2
We propose VecKM, a local point cloud geometry encoder that is descriptive and efficient to compute. VecKM leverages a unique approach by vectorizing a kernel mixture to represent…
conv_einsum: A Framework for Representation and Fast Evaluation of Multilinear Operations in Convolutional Tensorial Neural Networks
Tahseen Rabbani, Jiahao Su, Xiaoyu Liu +3
Modern ConvNets continue to achieve state-of-the-art results over a vast array of vision and image classification tasks, but at the cost of increasing parameters. One strategy for…
WAVES: Benchmarking the Robustness of Image Watermarks
Bang An, Mucong Ding, Tahseen Rabbani +8
In the burgeoning age of generative AI, watermarks act as identifiers of provenance and artificial content. We present WAVES (Watermark Analysis Via Enhanced Stress-testing), a ben…
Large-Scale Distributed Learning via Private On-Device Locality-Sensitive Hashing
Tahseen Rabbani, Marco Bornstein, Furong Huang
Locality-sensitive hashing (LSH) based frameworks have been used efficiently to select weight vectors in a dense hidden layer with high cosine similarity to an input, enabling dyna…
SWIFT: Rapid Decentralized Federated Learning via Wait-Free Model Communication
Marco Bornstein, Tahseen Rabbani, Evan Wang +2
The decentralized Federated Learning (FL) setting avoids the role of a potentially unreliable or untrustworthy central host by utilizing groups of clients to collaboratively train…
Comfetch: Federated Learning of Large Networks on Constrained Clients via Sketching
Tahseen Rabbani, Brandon Feng, Marco Bornstein +5
Federated learning (FL) is a popular paradigm for private and collaborative model training on the edge. In centralized FL, the parameters of a global architecture (such as a deep n…