Essam Sleiman

Essam Sleiman

I run Canvas Labs (YC), where we work on self-improving AI.

Previously, I did research on continual learning, language-model interpretability, and vision-language models at Amazon Science and as a grad student at Harvard, with papers at ECCV and CVPR. In my free time, I enjoy basketball, coffee, and hiking around SF.

Email GitHub Scholar X LinkedIn

Selected Work

Canvas Labs AutoHarnessBench A long-horizon SWE & self-improvement benchmark evaluating automatic harness optimization.
site benchmark evals coming soon
Privileged self-distillation: rollout, construct hint, distill
Canvas Labs Privileged Self-Distillation Essam Sleiman* · Preprint, 2026 A post-training method that distills training signal from failed rollouts corrected with privileged hints.
blog rl post-training
67%
→
80%
→
87%
Canvas Labs Meta-Agent An open-source framework for agent continual learning.
code agents self-improving ai
Continual Learning for AgentsMar 14 Reward Modeling as Harness OptimizationApr 22
Canvas Coworker — AI coworker for knowledge work
Canvas Labs Canvas Coworker An AI coworker for knowledge work.
site product agents
Research Engineer at Amazon Science Continual Self-Supervised Learning with Knowledge Distillation Essam Sleiman*, Xiangbo Li, Saad Ali · Preprint, 2023 A video embedding model for Twitch that learns new content without forgetting the old.
paper continual learning self-supervised
Goldfish long-video retrieval framework architecture
Research, Harvard Goldfish: Vision-Language Understanding of Arbitrarily Long Videos Essam Sleiman* (Contributor) · ECCV 2024 A SOTA vision-language model for question answering on hour-long videos.
paper code vision-language long video
Research, Harvard & MIT Do Function Vectors Factor Task and Distribution? Essam Sleiman*, Jacob Andreas · Preprint, 2024 An interpretability study of how LLMs represent tasks during in-context learning.
paper code interpretability in-context learning
SlowFormer energy attack on vision transformers
Research, UC Davis SlowFormer: Adversarial Robustness for Efficient Vision Transformers Essam Sleiman*, K L Navaneet*, et al. · CVPR 2024 A universal patch attack that maximizes the compute cost of efficient vision transformers.
paper code robustness vision transformers

→ See all projects