Bhiksha Raj

发表论文 67 篇 · 总被引 664 次 · h-index 12

代表论文

• Masked Autoencoders Are Effective Tokenizers for Diffusion Models (2025 · International Conference on Machine Learning · 被引 89)
• ADIFF: Explaining audio difference using natural language (2025 · International Conference on Learning Representations · 被引 12)
• Image Tokenizer Needs Post-Training (2025 · arXiv.org · 被引 10)
• Robust Latent Matters: Boosting Image Generation with Sampling Error Synthesis (2025 · arXiv.org · 被引 10)
• Scalable Benchmarking and Robust Learning for Noise-Free Ego-Motion and 3D Reconstruction from Noisy Video (2025 · International Conference on Learning Representations · 被引 10)
• SVeritas: Benchmark for Robust Speaker Verification under Diverse Conditions (2025 · Conference on Empirical Methods in Natural Language Processing · 被引 6)