Get started
Author

Sambit Sahu

Preference Tuning with Human Feedback on Language, Speech, and Vision Tasks: A Survey
2025 · Genta Indra Winata, Hanyang Zhao, et al. · Journal of Artificial Intelligence Research · 8
PDF
T1: A Tool-Oriented Conversational Dataset for Multi-Turn Agentic Planning
2025 · Amartya Chakraborty, Paresh Dashore, et al. · neural information processing systems · 2
RoleHear: Pseudo-Labeling for Semi-Supervised Role-Attributed Streaming Speech Recognition
2026 · Liu, Zefang, Zhu, Chenyang, et al. · arXiv (Cornell University)
PDF
Beyond Corrected Actions: Training LLM Agents on Textual Critiques
2026 · Zeng, Thomas, Cheng, Zelei, et al. · arXiv (Cornell University)
PDF
AdaGuard: Enhancing Safety and Policy Compliance with Reasoning-Enabled LLM-As-A-Judge Guardrails
2026 · Rad, Melissa Kazemi, Dai, Sihui, et al. · arXiv (Cornell University)
PDF
The Rise of Verbal Reinforcement Learning
2026 · Tayal, Kshitij, Sharma, Arun, et al. · arXiv (Cornell University)
PDF
StreamHear: Domain-Adapted Pseudo-Labeling for Semi-Supervised Streaming Speech Recognition
2026 · Liu, Zefang, Zhu, Chenyang, et al. · arXiv (Cornell University)
PDF
Efficient Reinforcement Learning for Long-Horizon Tool-Use Agentic Tasks
2026 · Cheng, Zelei, Mishra, Amritansh, et al. · arXiv (Cornell University)
PDF
Structured Thoughts For Improved Reasoning And Context Pruning
2026 · Sarwar, Zain, Chakraborty, Supriyo, et al. · arXiv (Cornell University)
PDF
Know When to Stop: Segment-Level Credit Assignment for Reducing Overthinking
2026 · Lee, Chia-Hsuan, Dai, Sihui, et al. · arXiv (Cornell University)
PDF
SEAD: Competence-Aware On-Policy Distillation via Entropy-Guided Supervision
2026 · Lee, Chia-Hsuan, Cheng, Zelei, et al. · arXiv (Cornell University)
PDF
Ask, Don't Judge: Binary Questions for Interpretable LLM Evaluation and Self-Improvement
2026 · Cho, Sangwoo, Chawla, Kushal, et al. · arXiv (Cornell University)
PDF
SAFARI: Scaling Long Horizon Agentic Fault Attribution via Active Investigation
2026 · Zhu, Chenyang, Yao, Jiayu, et al. · arXiv (Cornell University)
PDF
Towards Scalable Customization and Deployment of Multi-Agent Systems for Enterprise Applications
2026 · Dashore, Paresh, Kulkarni, Shreyas, et al. · arXiv (Cornell University)
PDF
Routing with Generated Data: Annotation-Free LLM Skill Estimation and Expert Selection
2026 · Association for Computational Linguistics 2026, Bansal, Mohit, et al. · Underline Science Inc.
MemGym: a Long-Horizon Memory Environment for LLM Agents
2026 · Xu, Wujiang, Wang, Yu, et al. · arXiv (Cornell University)
PDF
AVSD: Adaptive-View Self-Distillation by Balancing Consensus and Teacher-Specific Privileged Signals
2026 · Nguyen, Duy, Xiao, Hanqi, et al. · arXiv (Cornell University)
PDF
Know Thy Reasoner: Not All Language Models Explore Alike
2026 · Choraria, Moulik, Gerogiannis, Argyrios, et al. · arXiv (Cornell University)
PDF
Decomposing the Delta: What Do Models Actually Learn from Preference Pairs?
2026 · Lee, Chia-Hsuan, Zhou, Mingyang, et al. · arXiv (Cornell University)
PDF
Lessons from the Field: An Adaptable Lifecycle Approach to Applied Dialogue Summarization
2026 · Association for Computational Linguistics 2026, Babinsky, Erin, et al. · Underline Science Inc.
DIAL-SUMMER: A Structured Evaluation Framework of Hierarchical Errors in Dialogue Summaries
2026 · Ramnath, Sahana, Chitsazan, Nima, et al. · arXiv (Cornell University)
PDF
Routing with Generated Data: Annotation-Free LLM Skill Estimation and Expert Selection
2026 · Niu, Tianyi, Chen, Justin Chih-Yao, et al. · arXiv (Cornell University)
PDF
Lessons from the Field: An Adaptable Lifecycle Approach to Applied Dialogue Summarization
2026 · Chawla, Kushal, Zhu, Chenyang, et al. · arXiv (Cornell University)
PDF
SPARC-RAG: Adaptive Sequential–Parallel Scaling with Context Management for Retrieval-Augmented Generation
2026 · Yuxin Yang, Gangda Deng, et al. · Conference on Empirical Methods in Natural Language Processing (EMNLP)
PDF
Lessons from the Field: An Adaptable Lifecycle Approach to Applied Dialogue Summarization
2026 · Kushal Chawla, Chenyang Zhu, et al. · Conference of the European Chapter of the Association for Computational Linguistics
PDF
Works count: 33
Citation count: 10
H-index: 2
I10-index:
Year
Topic
Type