3 papers
cs.CL2026
CacheRL:Multi-Turn Tool-Calling Agents via Cached Rollouts and Hybrid Reward
Md Amirul Islam, Sumiran Thakur, Huancheng Chen +3
We present CacheRL, a system for training small agent foundation models that achieves 92 percent process accuracy on multi-step tool-calling tasks, approaching GPT-5's 94 percent w…
cs.CV2025
Few-Shot-Based Modular Image-to-Video Adapter for Diffusion Models
Zhenhao Li, Shaohan Yi, Zheng Liu +7
Diffusion models (DMs) have recently achieved impressive photorealism in image and video generation. However, their application to image animation remains limited, even when traine…
cs.AI2025
OmniScience: A Domain-Specialized LLM for Scientific Reasoning and Discovery
Vignesh Prabhakar, Md Amirul Islam, Adam Atanas +8
Large Language Models (LLMs) have demonstrated remarkable potential in advancing scientific knowledge and addressing complex challenges. In this work, we introduce OmniScience, a s…