Author

Roei Herzig

2 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Sep 2026

ContextFlow: In-Context Flow Matching for Robot Manipulation

Although highly effective in vision and language domains, applying in-context learning to robotics remains challenging. Existing autoregressive in-context imitation methods discretize continuous actions and exacerbate the accumulation of early prediction errors through next-token prediction, limiting their generalizati...

Jian Ding, Xian-Jie Dai, Roei Herzig et al. · 0 citations

#artificial intelligence Preprint Sep 2026

Discriminative World Models for Web Agents

Predicted-state matching, a training objective where the predicted representation must distinguish the true resulting state from those reached by alternative actions, is introduced and outperforms world models trained with supervised next-state prediction.

Kelvin Li, Dhruva Pendharkar, Anish Pahilajani et al. · 0 citations