0

Bhiksha Raj

Papers
19

Cite

Notes

Only stored in your browser.

Attribution

Affiliations & profile
Semantic Scholar
Attribution policy →
19papers

Authored papers

19

Masked Autoencoders Are Effective Tokenizers for Diffusion Models

arXiv 2025

2025

Robust Latent Matters: Boosting Image Generation with Sampling Error

arXiv 2025

2025

Image Tokenizer Needs Post-Training

arXiv 2025

2025

Mellow: a small audio language model for reasoning

arXiv 2025

2025

ControlVAR: Exploring Controllable Visual Autoregressive Modeling

arXiv 2024

2024

Audio Entailment: Assessing Deductive Reasoning for Audio Understanding

arXiv 2024

2024

$\text{R}^2$-Bench: Benchmarking the Robustness of Referring Perception Models under Perturbations

arXiv 2024

2024

Speech vs. Transcript: Does It Matter for Human Annotators in Speech Summarization?

arXiv 2024

2024

uDistil-Whisper: Label-Free Data Filtering for Knowledge Distillation in Low-Data Regimes

arXiv 2024

2024

Understanding and Mitigating the Label Noise in Pre-training on Downstream Tasks

arXiv 2023

2023

Token Prediction as Implicit Classification to Identify LLM-Generated Text

arXiv 2023

2023

FREDOM: Fairness Domain Adaptation Approach to Semantic Scene Understanding

CVPR 2023 1

2023

Training Audio Captioning Models without Audio

arXiv 2023

2023

GPT-Sentinel: Distinguishing Human and ChatGPT Generated Content

arXiv 2023

2023

HEAR: Holistic Evaluation of Audio Representations

arXiv 2022

2022

How many perturbations break this model? Evaluating robustness beyond adversarial accuracy

arXiv 2022

2022

USB: A Unified Semi-supervised Learning Benchmark for Classification

arXiv 2022

2022

Towards Robust Referring Video Object Segmentation with Cyclic Relational Consensus

arXiv 2022

2022

VLTinT: Visual-Linguistic Transformer-in-Transformer for Coherent Video Paragraph Captioning

arXiv 2022

2022

Affiliations

No known affiliations.

Frequent co-authors

10

from 19 papers