7 papers
AgentHorizon: Evaluating Agentic Judges for Long-Horizon Computer-Use Tasks
Xing Han Lù, Dheeraj Vattikonda, Sina Hajimiri +7
Computer-use agents are capable of completing complex tasks, increasing the use of automatic judges to determine success, either for training or for evaluation without human involv…
KV-streams for Efficient Compaction in Agentic Reinforcement Learning
Emiliano Penaloza, Dane Malenfant, Dheeraj Vattikonda +15
Scaling the horizon of agentic LLMs is bottlenecked by the need to fit ever longer context traces in GPU memory. Context compaction has been the most popular mechanism to alleviate…
Privileged Information Distillation for Language Models
Emiliano Penaloza, Dheeraj Vattikonda, Nicolas Gontier +3
Training-time privileged information (PI) can enable language models to succeed on tasks they would otherwise fail, making it a powerful tool for reinforcement learning in hard, lo…
How to Train Your LLM Web Agent: A Statistical Diagnosis
Dheeraj Vattikonda, Santhoshi Ravichandran, Emiliano Penaloza +13
LLM-based web agents have recently made significant progress, but much of it has occurred in closed-source systems, widening the gap with open-source alternatives. Progress has bee…
SLACK: Attacking LiDAR-based SLAM with Adversarial Point Injections
Prashant Kumar, Dheeraj Vattikonda, Kshitij Madhav Bhat +2
The widespread adoption of learning-based methods for the LiDAR makes autonomous vehicles vulnerable to adversarial attacks through adversarial \textit{point injections (PiJ)}. It…
Learning Action and Reasoning-Centric Image Editing from Videos and Simulations
Benno Krojer, Dheeraj Vattikonda, Luis Lara +4
An image editing model should be able to perform diverse edits, ranging from object replacement, changing attributes or style, to performing actions or movement, which require many…
Differentiable SLAM Helps Deep Learning-based LiDAR Perception Tasks
Prashant Kumar, Dheeraj Vattikonda, Vedang Bhupesh Shenvi Nadkarni +2
We investigate a new paradigm that uses differentiable SLAM architectures in a self-supervised manner to train end-to-end deep learning models in various LiDAR based applications.…