20 citations · 32 across the 20 of their papers we have counts for
23 papers
Mosaic: Runtime-Efficient Multi-Agent Embodied Planning
Kunjal Panchal, Saayan Mitra, Sunav Choudhary +3
LLM-based multi-agent embodied planning remains impractical due to prohibitively high execution latency. We identify failed actions as the dominant bottleneck, stemming from two co…
BACON: Budgeted Human Calibration for Modeling and Evaluation with Multiple AI Judges
Lei Shi, Anlan Zhang, Rita Lyu +6
AI judges offer a scalable, low-cost alternative to human evaluation, but their outputs can be biased relative to human preferences and highly item-dependent, varying across judges…
An Interactive Paradigm for Deep Research
Lin Ai, Victor S. Bursztyn, Xiang Chen +2
Recent advances in large language models (LLMs) have enabled deep research systems that synthesize comprehensive, report-style answers to open-ended queries by combining retrieval,…
TeamFusion: Supporting Open-ended Teamwork with Multi-Agent Systems
Jiale Liu, Victor S. Bursztyn, Lin Ai +4
In open-ended domains, teams must reconcile diverse viewpoints to produce strong deliverables. Answer aggregation approaches commonly used in closed domains are ill-suited to this…
ThinkRouter: Efficient Reasoning via Routing Thinking between Latent and Discrete Spaces
Xin Xu, Tong Yu, Xiang Chen +3
Recent work explores latent reasoning to improve reasoning efficiency by replacing explicit reasoning trajectories with continuous representations in a latent space, yet its effect…
Atom: Efficient On-Device Video-Language Pipelines Through Modular Reuse
Kunjal Panchal, Saayan Mitra, Somdeb Sarkhel +4
Recent advances in video-language models have enabled powerful applications like video retrieval, captioning, and assembly. However, executing such multi-stage pipelines efficientl…
Mitigating Forgetting Between Supervised and Reinforcement Learning Yields Stronger Reasoners
Xiangchi Yuan, Xiang Chen, Tong Yu +4
Large Language Models (LLMs) show strong reasoning abilities, often amplified by Chain-of-Thought (CoT) prompting and reinforcement learning (RL). Although RL algorithms can substa…
A Penalty Goes a Long Way: Measuring Lexical Diversity in Synthetic Texts Under Prompt-Influenced Length Variations
Vijeta Deshpande, Ishita Dasgupta, Uttaran Bhattacharya +3
Synthetic text generated by Large Language Models (LLMs) is increasingly used for further training and improvement of LLMs. Diversity is crucial for the effectiveness of synthetic…
Shape My Moves: Text-Driven Shape-Aware Synthesis of Human Motions
Ting-Hsuan Liao, Yi Zhou, Yu Shen +4
We explore how body shapes influence human motion synthesis, an aspect often overlooked in existing text-to-motion generation methods due to the ease of learning a homogenized, can…
SKALD: Learning-Based Shot Assembly for Coherent Multi-Shot Video Creation
Chen Yi Lu, Md Mehrab Tanjim, Ishita Dasgupta +4
We present SKALD, a multi-shot video assembly method that constructs coherent video sequences from candidate shots with minimal reliance on text. Central to our approach is the Lea…
Detecting Ambiguities to Guide Query Rewrite for Robust Conversations in Enterprise AI Assistants
Md Mehrab Tanjim, Xiang Chen, Victor S. Bursztyn +8
Multi-turn conversations with an Enterprise AI Assistant can be challenging due to conversational dependencies in questions, leading to ambiguities and errors. To address this, we…
CodeLutra: Boosting LLM Code Generation via Preference-Guided Refinement
Leitian Tao, Xiang Chen, Tong Yu +4
Large Language Models (LLMs) have revolutionized code generation but require significant resources and often over-generalize, limiting their task-specific efficiency. Fine-tuning s…
A/B testing under Interference with Partial Network Information
Shiv Shankar, Ritwik Sinha, Yash Chandak +2
A/B tests are often required to be conducted on subjects that might have social connections. For e.g., experiments on social media, or medical and social interventions to control t…
HanDiffuser: Text-to-Image Generation With Realistic Hand Appearances
Supreeth Narasimhaswamy, Uttaran Bhattacharya, Xiang Chen +3
Text-to-image generative models can generate high-quality humans, but realism is lost when generating hands. Common artifacts include irregular hand poses, shapes, incorrect number…
SODA: Protecting Proprietary Information in On-Device Machine Learning Models
Akanksha Atrey, Ritwik Sinha, Saayan Mitra +1
The growth of low-end hardware has led to a proliferation of machine learning-based services in edge applications. These applications gather contextual information about users and…
Fast Heavy Inner Product Identification Between Weights and Inputs in Neural Network Training
Lianke Qin, Saayan Mitra, Zhao Song +2
In this paper, we consider a heavy inner product identification problem, which generalizes the Light Bulb problem~(\cite{prr89}): Given two sets and $B \sub…
Decentralized Personalized Online Federated Learning
Renzhi Wu, Saayan Mitra, Xiang Chen +1
Vanilla federated learning does not support learning in an online environment, learning a personalized model on each client, and learning in a decentralized setting. There are exis…
Token-Level Adversarial Prompt Detection Based on Perplexity Measures and Contextual Information
Zhengmian Hu, Gang Wu, Saayan Mitra +4
In recent years, Large Language Models (LLM) have emerged as pivotal tools in various applications. However, these models are susceptible to adversarial prompt attacks, where attac…
ToolChain*: Efficient Action Space Navigation in Large Language Models with A* Search
Yuchen Zhuang, Xiang Chen, Tong Yu +5
Large language models (LLMs) have demonstrated powerful decision-making and planning capabilities in solving complicated real-world problems. LLM-based autonomous agents can intera…
Privacy Aware Experiments without Cookies
Shiv Shankar, Ritwik Sinha, Saayan Mitra +3
Consider two brands that want to jointly test alternate web experiences for their customers with an A/B test. Such collaborative tests are today enabled using \textit{third-party c…
DiPS: Differentiable Policy for Sketching in Recommender Systems
Aritra Ghosh, Saayan Mitra, Andrew Lan
In sequential recommender system applications, it is important to develop models that can capture users' evolving interest over time to successfully recommend future items that the…
Optimal Bidding Strategy without Exploration in Real-time Bidding
Aritra Ghosh, Saayan Mitra, Somdeb Sarkhel +1
Maximizing utility with a budget constraint is the primary goal for advertisers in real-time bidding (RTB) systems. The policy maximizing the utility is referred to as the optimal…
Scalable Bid Landscape Forecasting in Real-time Bidding
Aritra Ghosh, Saayan Mitra, Somdeb Sarkhel +3
In programmatic advertising, ad slots are usually sold using second-price (SP) auctions in real-time. The highest bidding advertiser wins but pays only the second-highest bid (know…