Bhiksha Raj

10

Papers

145

Total Citations

Papers (10)

ImageFolder: Autoregressive Image Generation with Folded Tokens

SoftVQ-VAE: Efficient 1-Dimensional Continuous Tokenizer

Audio Entailment: Assessing Deductive Reasoning for Audio Understanding

Synergistic Global-space Camera and Human Reconstruction from Videos

ADIFF: Explaining audio difference using natural language

FALCON: Fairness Learning via Contrastive Attention Approach to Continual Semantic Scene Understanding

Toward Material-Agnostic System Identification from Videos

QDFormer: Towards Robust Audiovisual Segmentation in Complex Environments with Quantization-based Semantic Decomposition

A General Framework for Learning from Weak Supervision

Completing Visual Objects via Bridging Generation and Segmentation