8 citations · 8 across the 5 of their papers we have counts for
7 papers
ReMedI: Inference-Time Refinement and Self-Distillation for Controllable Molecular Optimization
Jia Yi Zhang, Shivanshu Shekhar, Allison McLevige +1
In drug development, lead optimization must improve competing properties, such as increasing permeability and reducing toxicity, while limiting scaffold changes that could compromi…
Spend Where It Matters: Particle Search with MH Refinement for Budget-Constrained Audio-Visual Alignment
Shivanshu Shekhar, Raghavendra Addanki, Tong Zhang +1
Reward-guided inference-time alignment can improve joint audio-visual generation, but optimizing multiple alignment objectives requires many expensive model evaluations, making exi…
VASR: Variance-Aware Systematic Resampling for Reward-Guided Diffusion
Shivanshu Shekhar, Sagnik Mukherjee, Jia Yi Zhang +1
Sequential Monte Carlo (SMC) samplers for reward-guided diffusion models often suffer from rapid lineage collapse: a few high-reward particles dominate the population within a hand…
GT-SVJ: Generative-Transformer-Based Self-Supervised Video Judge For Efficient Video Reward Modeling
Shivanshu Shekhar, Uttaran Bhattacharya, Raghavendra Addanki +3
Aligning video generative models with human preferences remains challenging: current approaches rely on Vision-Language Models (VLMs) for reward modeling, but these models struggle…
ROCM: RLHF on consistency models
Shivanshu Shekhar, Tong Zhang
Diffusion models have revolutionized generative modeling in continuous domains like image, audio, and video synthesis. However, their iterative sampling process leads to slow gener…
SEE-DPO: Self Entropy Enhanced Direct Preference Optimization
Shivanshu Shekhar, Shreyas Singh, Tong Zhang
Direct Preference Optimization (DPO) has been successfully used to align large language models (LLMs) according to human preferences, and more recently it has also been applied to…
Towards Optimizing the Costs of LLM Usage
Shivanshu Shekhar, Tanishq Dubey, Koyel Mukherjee +3
Generative AI and LLMs in particular are heavily used nowadays for various document processing tasks such as question answering and summarization. However, different LLMs come with…