collaborators

5 papers

cs.AI2026

BRIDGE: Predicting Human Task Completion Time From Model Performance

Fengyuan Liu, Jay Gala, Nilaksh +3

Evaluating the real-world capabilities of AI systems requires grounding benchmark performance in human-interpretable measures of task difficulty. Existing approaches that rely on d…

cs.CV2026

Reconstruction or Semantics? What Makes a Latent Space Useful for Robotic World Models

Nilaksh, Saurav Jha, Artem Zholus +1

World model-based policy evaluation is a practical proxy for testing real-world robot control by rolling out candidate actions in action-conditioned video diffusion models. As thes…

cs.AI2025

V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning

Mido Assran, Adrien Bardes, David Fan +27

A major challenge for modern AI is to learn to understand the world and learn to act largely by observation. This paper explores a self-supervised approach that combines internet-s…

cs.AI2025

Boosting LLM Reasoning via Spontaneous Self-Correction

Xutong Zhao, Tengyu Xu, Xuewei Wang +11

While large language models (LLMs) have demonstrated remarkable success on a broad range of tasks, math reasoning remains a challenging one. One of the approaches for improving mat…

cs.AI2025

Combining Domain and Alignment Vectors to Achieve Better Knowledge-Safety Trade-offs in LLMs

Megh Thakkar, Quentin Fournier, Matthew Riemer +4

There is a growing interest in training domain-expert LLMs that excel in specific technical fields compared to their general-purpose instruction-tuned counterparts. However, these…