AIConfPaper
← Search

Sandeep P. Chinchali

19 accepted papers

2026

DiffVax: Optimization-Free Image Immunization Against Diffusion-Based Editing

Tarik Can Ozden, Ozgur Kara, Oguzhan Akcin, Kerem Zaman, Shashank Srivastava, Sandeep P. Chinchali +1
ICLR 2026poster

Current image immunization defense techniques against diffusion-based editing embed imperceptible noise into target images to disrupt editing models. However, these methods face scalability challenges, as they require time-consuming optimization for each image separately, taking hours for small batc…

Cited by 0Source ↗code ↗Scholar ↗
2025

CSA: Data-efficient Mapping of Unimodal Features to Multimodal Features

Po-han Li, Sandeep P. Chinchali, ufuk topcu
ICLR 2025poster

Multimodal encoders like CLIP excel in tasks such as zero-shot image classification and cross-modal retrieval. However, they require excessive training data. We propose canonical similarity analysis (CSA), which uses two unimodal encoders to replicate multimodal encoders using limited data. CSA maps…

Cited by 0Source ↗PDF ↗Scholar ↗
2025

Constrained Posterior Sampling: Time Series Generation with Hard Constraints

Sai Shankar Narasimhan, Shubhankar Agarwal, Litu Rout, Sanjay Shakkottai, Sandeep P. Chinchali
NeurIPS 2025poster

Generating realistic time series samples is crucial for stress-testing models and protecting user privacy by using synthetic data. In engineering and safety-critical applications, these samples must meet certain hard constraints that are domain-specific or naturally imposed by physics or nature. Con…

Cited by 0Source ↗Scholar ↗
2025

Distributed Upload and Active Labeling for Resource-Constrained Fleet Learning

Oguzhan Akcin, Harsh Goel, Ruihan Zhao, Sandeep P. Chinchali
CoRL 2025poster

In multi-robot systems, fleets are often deployed to collect data that improves the performance of machine learning models for downstream perception and planning. However, real-world robotic deployments generate vast amounts of data across diverse conditions, while only a small portion can be transm…

Cited by 0Source ↗Scholar ↗
2025

Exploiting Distribution Constraints for Scalable and Efficient Image Retrieval

Mohammad Omama, Po-han Li, Sandeep P. Chinchali
ICLR 2025poster

Image retrieval is crucial in robotics and computer vision, with downstream applications in robot place recognition and vision-based product recommendations. Modern retrieval systems face two key challenges: scalability and efficiency. State-of-the-art image retrieval systems train specific neural n…

Cited by 0Source ↗PDF ↗Scholar ↗
2025

R3DM: Enabling Role Discovery and Diversity Through Dynamics Models in Multi-agent Reinforcement Learning

Harsh Goel, Mohammad Omama, Behdad Chalaki, Vaishnav Tadiparthi, Ehsan Moradi Pari, Sandeep P. Chinchali
ICML 2025poster

Multi-agent reinforcement learning (MARL) has achieved significant progress in large-scale traffic control, autonomous vehicles, and robotics. Drawing inspiration from biological systems where roles naturally emerge to enable coordination, role-based MARL methods have been proposed to enhance cooper…

Cited by 0Source ↗PDF ↗code ↗Scholar ↗
2025

VIBE: Annotation-Free Video-to-Text Information Bottleneck Evaluation for TL;DR

Shenghui Chen, Po-han Li, Sandeep P. Chinchali, ufuk topcu
NeurIPS 2025poster

Many decision-making tasks, where both accuracy and efficiency matter, still require human supervision. For example, tasks like traffic officers reviewing hour-long dashcam footage or researchers screening conference videos can benefit from concise summaries that reduce cognitive load and save time.…

Cited by 0Source ↗Scholar ↗
2024

Accelerating Visual Sparse-Reward Learning with Latent Nearest-Demonstration-Guided Explorations

Ruihan Zhao, ufuk topcu, Sandeep P. Chinchali, Mariano Phielipp
CoRL 2024poster

Recent progress in deep reinforcement learning (RL) and computer vision enables artificial agents to solve complex tasks, including locomotion, manipulation, and video games from high-dimensional pixel observations. However, RL usually relies on domain-specific reward functions for sufficient learni…

Cited by 0Source ↗Scholar ↗
2024

Fleet Supervisor Allocation: A Submodular Maximization Approach

Oguzhan Akcin, Ahmet Ege Tanriverdi, Kaan Kale, Sandeep P. Chinchali
CoRL 2024poster

In real-world scenarios, the data collected by robots in diverse and unpredictable environments is crucial for enhancing their perception and decision-making models. This data is predominantly collected under human supervision, particularly through imitation learning (IL), where robots learn complex…

Cited by 0Source ↗Scholar ↗
2024

Time Weaver: A Conditional Time Series Generation Model

Sai Shankar Narasimhan, Shubhankar Agarwal, Oguzhan Akcin, sujay sanghavi, Sandeep P. Chinchali
ICML 2024spotlight

Imagine generating a city’s electricity demand pattern based on weather, the presence of an electric vehicle, and location, which could be used for capacity planning during a winter freeze. Such real-world time series are often enriched with paired heterogeneous contextual metadata (e.g., weather an…

Cited by 17Source ↗PDF ↗Scholar ↗
2023

Robust Forecasting for Robotic Control: A Game-Theoretic Approach

Shubhankar Agarwal, David Fridovich-Keil, Sandeep P. Chinchali
ICRA 2023poster

Modern robots require accurate forecasts to make optimal decisions in the real world. For example, self-driving cars need an accurate forecast of other agents' future actions to plan safe trajectories. Current methods rely heavily on historical time series to accurately predict the future. However,…

Cited by 5Source ↗Scholar ↗
2023

Task-aware Distributed Source Coding under Dynamic Bandwidth

Po-han Li, Sravan Kumar Ankireddy, Ruihan Zhao, Hossein Nourkhiz Mahjoub, Ehsan Moradi Pari, ufuk topcu +2
NeurIPS 2023poster

Efficient compression of correlated data is essential to minimize communication overload in multi-sensor networks. In such networks, each sensor independently compresses the data and transmits them to a central node. A decoder at the central node decompresses and passes the data to a pre-trained mac…

Cited by 10Source ↗PDF ↗code ↗Scholar ↗
2022

Class-Aware Adversarial Transformers for Medical Image Segmentation

Chenyu You, Ruihan Zhao, Fenglin Liu, Siyuan Dong, Sandeep P. Chinchali, ufuk topcu +2
NeurIPS 2022accept

Transformers have made remarkable progress towards modeling long-range dependencies within the medical image analysis domain. However, current transformer-based models suffer from several disadvantages: (1) existing methods fail to capture the important features of the images due to the naive tokeni…

Cited by 163Source ↗PDF ↗Scholar ↗
2022

Decentralized Data Collection for Robotic Fleet Learning: A Game-Theoretic Approach

Oguzhan Akcin, Po-han Li, Shubhankar Agarwal, Sandeep P. Chinchali
CoRL 2022poster

Fleets of networked autonomous vehicles (AVs) collect terabytes of sensory data, which is often transmitted to central servers (the ``cloud'') for training machine learning (ML) models. Ideally, these fleets should upload all their data, especially from rare operating contexts, in order to train rob…

Cited by 6Source ↗Scholar ↗
2021

Data Sharing and Compression for Cooperative Networked Control

Jiangnan Cheng, Marco Pavone, Sachin Katti, Sandeep P. Chinchali, Ao Tang
NeurIPS 2021poster

Sharing forecasts of network timeseries data, such as cellular or electricity load patterns, can improve independent control applications ranging from traffic scheduling to power generation. Typically, forecasts are designed without knowledge of a downstream controller's task objective, and thus sim…

Cited by 14Source ↗PDF ↗code ↗Scholar ↗
2016

Simultaneous model identification and task satisfaction in the presence of temporal logic constraints

Sandeep P. Chinchali, Scott C. Livingston, Marco Pavone, Joel W. Burdick
ICRA 2016

Recent proliferation of cyber-physical systems, ranging from autonomous cars to nuclear hazard inspection robots, has exposed several challenging research problems on automated fault detection and recovery. This paper considers how recently developed formal synthesis and model verification technique

Cited by 5Source ↗Scholar ↗