Aman Gupta

4 papers · 2024–2025 · 3 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Bronze 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (12) 👥 Mega-Team · Squad

Venues

ICML (2) EMNLP (1) ICLR (1)

Top co-authors

Shao Tang (3) Jiwoo Hong (2) Noah Lee (2) Eunki Kim (2) Sirou Zhu (2) Qingquan Song (2) Natesh S. Pillai (2) Siyu Zhu (2) Gregory Dexter (2) Sathiya Keerthi (2)

Research topics

Machine Learning (4) Optimization & Theory · Machine Learning (3) Artificial Intelligence (2) Reinforcement Learning (2) Core AI (2) Methods (2) Deep Learning (1) Application Areas (1) Learning Types (1) Optimization & Theory · Deep Learning (1)

Keywords

model compression (1) model quantization (1) direct preference optimization (1) knowledge distillation (1) efficient computing (1) generalization error (1) bradley-terry model (1) reward model (1) recommendation system (1) recommender system (1) structured pruning (1) small language model (1) sgd stability (1) linear stability (1) loss hessian (1) loss surface geometry (1) rlhf (1) overoptimization (1) generalizability (1) alphapo (1)

Papers

AlphaPO: Reward Shape Matters for LLM Alignment ICML 2025 On the Robustness of Reward Models for Language Model Alignment ICML 2025 Scaling Down, Serving Fast: Compressing and Deploying Efficient LLMs for Recommendation Systems EMNLP 2025 A Precise Characterization of SGD Stability Using Loss Surface Geometry ICLR 2024