Good Papers

Showing papers from University at Buffalo, State University of New York Show all papers

75%Highly rated
?Highly ratedVote to see the score
NeurIPS 2026New YorkUniversity at Buffalo, State UniMonashRL for LLMs

Rationale-Guided Policy Optimization: Learning to Reason with Adaptive Rationale Scaffolding

RGPO adaptively uses ground-truth rationales as temporary scaffolds to generate improved responses for on-policy RL, then transfers only higher-reward model outputs back, reducing reward sparsity and improving text and multimodal reasoning.

Hoang Phan, Minh Pham, Chau Pham, Chinmay Hegde and 2 more

Published Oct 5, 2026 · ▲ 21 on Hugging Face · Code ★ 1

– Readers
10/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in to vote.

AI panel: 10 of 20 reviewers recommend it
lenient 4/5
medium 6/10
strict 0/5
68%Highly rated
?Highly ratedVote to see the score
CVPR 2025University at Buffalo, State UniNew YorkVision-language models

PLVM: A Tuning-Free Approach for Personalized Large Vision-Language Model

PLVM introduces a tuning-free Aligner for personalized large vision-language models that recognizes referential concepts during dialogue with negligible extra cost.

Chau Pham, Hoang Phan, David Doermann, Yunjie Tian

Published Jun 11, 2025 · 1 citation

– Readers
4/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in to vote.

AI panel: 4 of 20 reviewers recommend it
lenient 4/5
medium 0/10
strict 0/5
69%Highly rated
?Highly ratedVote to see the score
International conference Recent advances in natural language processing 2025NortheasternCarnegie MellonU California San DiegoU Maryland, College ParkUniversity at Buffalo, State UniQuantization

A Survey on Small Language Models

This survey reviews small language model architectures, training, and compression via a novel optimization taxonomy and highlights open challenges.

Chien Van Nguyen, Xuan Shen, Ryan Aponte, Yu Xia and 29 more

Published 2025 · 22 citations

– Readers
6/21 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in to vote.

AI panel: 6 of 21 reviewers recommend it
lenient 5/5
medium 1/11
strict 0/5