no code implementations • 7 Nov 2024 • Leitian Tao, Xiang Chen, Tong Yu, Tung Mai, Ryan Rossi, Yixuan Li, Saayan Mitra
By learning from both successes and mistakes, CodeLutra provides a scalable and efficient path to high-quality code generation, making smaller open-source models more competitive with leading closed-source alternatives.
no code implementations • 16 Apr 2024 • Shiv Shankar, Ritwik Sinha, Yash Chandak, Saayan Mitra, Madalina Fiterau
A/B tests are often required to be conducted on subjects that might have social connections.
no code implementations • CVPR 2024 • Supreeth Narasimhaswamy, Uttaran Bhattacharya, Xiang Chen, Ishita Dasgupta, Saayan Mitra, Minh Hoai
To generate images with realistic hands, we propose a novel diffusion-based architecture called HanDiffuser that achieves realism by injecting hand embeddings in the generative process.
no code implementations • 22 Dec 2023 • Akanksha Atrey, Ritwik Sinha, Saayan Mitra, Prashant Shenoy
The growth of low-end hardware has led to a proliferation of machine learning-based services in edge applications.
no code implementations • 20 Nov 2023 • Zhengmian Hu, Gang Wu, Saayan Mitra, Ruiyi Zhang, Tong Sun, Heng Huang, Viswanathan Swaminathan
Our work aims to address this concern by introducing a novel approach to detecting adversarial prompts at a token level, leveraging the LLM's capability to predict the next token's probability.
no code implementations • 19 Nov 2023 • Lianke Qin, Saayan Mitra, Zhao Song, Yuanyuan Yang, Tianyi Zhou
In this paper, we consider a heavy inner product identification problem, which generalizes the Light Bulb problem~(\cite{prr89}): Given two sets $A \subset \{-1,+1\}^d$ and $B \subset \{-1,+1\}^d$ with $|A|=|B| = n$, if there are exact $k$ pairs whose inner product passes a certain threshold, i. e., $\{(a_1, b_1), \cdots, (a_k, b_k)\} \subset A \times B$ such that $\forall i \in [k], \langle a_i, b_i \rangle \geq \rho \cdot d$, for a threshold $\rho \in (0, 1)$, the goal is to identify those $k$ heavy inner products.
no code implementations • 8 Nov 2023 • Renzhi Wu, Saayan Mitra, Xiang Chen, Anup Rao
Therefore, we propose a new learning setting \textit{Decentralized Personalized Online Federated Learning} that considers all the three aspects at the same time.
no code implementations • 20 Oct 2023 • Yuchen Zhuang, Xiang Chen, Tong Yu, Saayan Mitra, Victor Bursztyn, Ryan A. Rossi, Somdeb Sarkhel, Chao Zhang
It formulates the entire action space as a decision tree, where each node represents a possible API function call involved in a solution plan.
no code implementations • 3 Nov 2022 • Shiv Shankar, Ritwik Sinha, Saayan Mitra, Viswanathan Swaminathan, Sridhar Mahadevan, Moumita Sinha
We propose a two-stage experimental design, where the two brands only need to agree on high-level aggregate parameters of the experiment to test the alternate experiences.
no code implementations • 8 Dec 2021 • 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 they are likely to interact with.
no code implementations • 31 Mar 2020 • Aritra Ghosh, Saayan Mitra, Somdeb Sarkhel, Viswanathan Swaminathan
Earlier works on optimal bidding strategy apply model-based batch reinforcement learning methods which can not generalize to unknown budget and time constraint.
no code implementations • 18 Jan 2020 • Aritra Ghosh, Saayan Mitra, Somdeb Sarkhel, Jason Xie, Gang Wu, Viswanathan Swaminathan
The highest bidding advertiser wins but pays only the second-highest bid (known as the winning price).