1 citations · 1 across the 17 of their papers we have counts for
19 papers
SpectralCanary: Embarrassingly Simple Low-Frequency Traces for T2I Dataset-Use Auditing
Sy-Tuyen Ho, Anirudh Satheesh, Soham Chawathe +4
Auditing whether a text-to-image (T2I) model was fine-tuned on a particular image collection is difficult: a model can absorb collection-level visual characteristics without reprod…
The Low Frequency Trap: Video Language Models Fail at Simple Event Bookkeeping
Sarvesh Baskar, Zikui Cai, Shayan Shabihi +5
Real-world video benchmarks provide broad coverage, but their fixed clips entangle event count, rate, duration, and visual complexity, making failure modes hard to isolate. While e…
DADiff: Diffusion-Driven Cross-Domain Policy Adaptation for Reinforcement Learning
Hanyang Chen, Anirudh Satheesh, Longchao Da +1
Transferring policies across domains poses a vital challenge in reinforcement learning, due to the dynamics mismatch between the source and target domains. In this paper, we consid…
Compositional Adversarial Training for Robust Visual Watermarking
Anirudh Satheesh, Michael-Andrei Panaitescu-Liess, Andrew Xu +4
Robust watermarking is typically trained with random post-processing augmentation, but random sampling under-covers the combinatorial space of realistic attack pipelines and rarely…
Global Convergence of Average Reward Constrained MDPs with Neural Critic and General Policy Parameterization
Anirudh Satheesh, Pankaj Kumar Barman, Washim Uddin Mondal +1
We study infinite-horizon Constrained Markov Decision Processes (CMDPs) with general policy parameterizations and multi-layer neural network critics. Existing theoretical analyses…
Provably Efficient Algorithms for S- and Non-Rectangular Robust MDPs with General Parameterization
Anirudh Satheesh, Ziyi Chen, Furong Huang +1
We study robust Markov decision processes (RMDPs) with general policy parameterization under s-rectangular and non-rectangular uncertainty sets. Prior work is largely limited to ta…
Regret Analysis of Unichain Average Reward Constrained MDPs with General Parameterization
Anirudh Satheesh, Vaneet Aggarwal
We study infinite-horizon average-reward constrained Markov decision processes (CMDPs) under the unichain assumption and general policy parameterizations. Existing regret analyses…
Primal-Only Actor Critic Algorithm for Robust Constrained Average Cost MDPs
Anirudh Satheesh, Sooraj Sathish, Swetha Ganesh +2
In this work, we study the problem of finding robust and safe policies in Robust Constrained Average-Cost Markov Decision Processes (RCMDPs). A key challenge in this setting is the…
Distributionally Robust Self Paced Curriculum Reinforcement Learning
Anirudh Satheesh, Keenan Powell, Vaneet Aggarwal
A central challenge in reinforcement learning is that policies trained in controlled environments often fail under distribution shifts at deployment into real-world environments. D…
Uncertainty-Aware Answer Selection for Improved Reasoning in Multi-LLM Systems
Aakriti Agrawal, Rohith Aralikatti, Anirudh Satheesh +3
Large Language Models (LLMs) have demonstrated exceptional capabilities, yet selecting the most reliable response from multiple LLMs remains a challenge, particularly in resource-c…
cMALC-D: Contextual Multi-Agent LLM-Guided Curriculum Learning with Diversity-Based Context Blending
Anirudh Satheesh, Keenan Powell, Hua Wei
Many multi-agent reinforcement learning (MARL) algorithms are trained in fixed simulation environments, making them brittle when deployed in real-world scenarios with more complex…
PICore: Physics-Informed Unsupervised Coreset Selection for Data Efficient Neural Operator Training
Anirudh Satheesh, Anant Khandelwal, Mucong Ding +1
Neural operators offer a powerful paradigm for solving partial differential equations (PDEs) that cannot be solved analytically by learning mappings between function spaces. Howeve…
MORSE-500: A Programmatically Controllable Video Benchmark to Stress-Test Multimodal Reasoning
Zikui Cai, Andrew Wang, Anirudh Satheesh +10
Despite rapid advances in vision-language models (VLMs), current benchmarks for multimodal reasoning fall short in three key dimensions. First, they overwhelmingly rely on static i…
EnsemW2S: Enhancing Weak-to-Strong Generalization with Large Language Model Ensembles
Aakriti Agrawal, Mucong Ding, Zora Che +6
With Large Language Models (LLMs) rapidly approaching and potentially surpassing human-level performance, it has become imperative to develop approaches capable of effectively supe…
Jailbreak Distillation: Renewable Safety Benchmarking
Jingyu Zhang, Ahmed Elgohary, Xiawei Wang +5
Large language models (LLMs) are rapidly deployed in critical applications, raising urgent needs for robust safety benchmarking. We propose Jailbreak Distillation (JBDistill), a no…
A Constrained Multi-Agent Reinforcement Learning Approach to Autonomous Traffic Signal Control
Anirudh Satheesh, Keenan Powell
Traffic congestion in modern cities is exacerbated by the limitations of traditional fixed-time traffic signal systems, which fail to adapt to dynamic traffic patterns. Adaptive Tr…
Model Tampering Attacks Enable More Rigorous Evaluations of LLM Capabilities
Zora Che, Stephen Casper, Robert Kirk +12
Evaluations of large language model (LLM) risks and capabilities are increasingly being incorporated into AI risk management and governance frameworks. Currently, most risk evaluat…
SAFLEX: Self-Adaptive Augmentation via Feature Label Extrapolation
Mucong Ding, Bang An, Yuancheng Xu +2
Data augmentation, a cornerstone technique in deep learning, is crucial in enhancing model performance, especially with scarce labeled data. While traditional techniques are effect…
EnsemW2S: Enhancing Weak-to-Strong Generalization with Large Language Model Ensembles
Aakriti Agrawal, Mucong Ding, Zora Che +6
With Large Language Models (LLMs) rapidly approaching and potentially surpassing human-level performance, it has become imperative to develop approaches capable of effectively supe…