3 papers
cs.CV2026
Foresight: planning future perception in streaming VLMs without retraining
Ashok Prasad Neupane, Dipan Bartaula, Ankit Belbase +5
Existing streaming vision-language models (VLMs) continuously perceive and reason over visual streams, but their computational pathways remain fixed throughout inference. Consequen…
cs.LG2026
iADD: Improving Alignment and Diversity in Diffusion Policy Optimization
Ashok Prasad Neupane, Saugat Adhikari, Pramish Paudel +2
Reinforcement learning based post training of diffusion models, such as Denoising Diffusion Policy Optimization (DDPO), optimizes a reverse diffusion process under a reward functio…
cs.AI2026
iARCS: Iterative Agentic RL for Controllable 3D Scene Generation
Saugat Adhikari, Ashok Prasad Neupane, Pramish Paudel +2
Synthetic 3D scene generation is increasingly used as a data source for computer vision and embodied AI, but existing generators often optimize perceptual realism without reliably…