Rishabh Tiwari

机构：UC Berkeley

发表论文 23 篇 · 总被引 831 次 · h-index 6

代表论文

• Why Do Multi-Agent LLM Systems Fail? (2025 · Neural Information Processing Systems · 被引 610)
• GCR: Gradient Coreset based Replay Buffer Selection for Continual Learning (2021 · Computer Vision and Pattern Recognition · 被引 188)
• Interactive Concept Bottleneck Models (2022 · AAAI Conference on Artificial Intelligence · 被引 107)
• The Art of Scaling Reinforcement Learning Compute for LLMs (2025 · arXiv.org · 被引 90)
• ChipNet: Budget-Aware Pruning with Heaviside Continuous Approximations (2021 · International Conference on Learning Representations · 被引 34)
• Using Early Readouts to Mediate Featural Bias in Distillation (2023 · IEEE Workshop/Winter Conference on Applications of Computer Vision · 被引 11)