activity
20242026
collaborators

11 papers

cs.CL2026

RIMS: Preference Optimization via Smoothed Multi-pair Aggregation for Small-Scale LLM Retrieval-Augmented Generation

Pei Tian, Zihan Dong, Tianci Liu +2

Small-scale language models (SLMs) are attractive for retrieval-augmented generation (RAG) in resource-constrained settings, but their limited capacity makes them highly sensitive…

cs.AI2026

Personalization as Inverse Planning: Learning Latent Design Intents for Agentic Slide Generation via Structural Denoising

Tianci Liu, Zihan Dong, Linjun Zhang +6

Slide design requires personalizing both deck themes and page layouts. Yet, current AI agent-based methods struggle with fine-grained, page-level design. Solely relying on prespeci…

cs.LG2026

RUBRIC-ARROW: Alternating Pointwise Rubric Reward Modeling for LLM Post-training in Non-verifiable Domains

Haoxiang Jiang, Zihan Dong, Tianci Liu +5

Pointwise reward modeling offers critical signals for LLM post-training, yet struggles with absolute scoring in subjective, non-verifiable settings. Rubric-based methods address th…

cs.CL2026

Alternating Reinforcement Learning for Rubric-Based Reward Modeling in Non-Verifiable LLM Post-Training

Ran Xu, Tianci Liu, Zihan Dong +6

Standard reward models typically predict scalar scores that fail to capture the multifaceted nature of response quality in non-verifiable domains, such as creative writing or open-…

cs.CL2026

OpenRubrics: Towards Scalable Synthetic Rubric Generation for Reward Modeling and LLM Alignment

Tianci Liu, Ran Xu, Tony Yu +4

Reward modeling lies at the core of reinforcement learning from human feedback (RLHF), yet most existing reward models rely on scalar or pairwise judgments that fail to capture the…

cs.LG2025

PEANuT: Parameter-Efficient Adaptation with Weight-aware Neural Tweakers

Yibo Zhong, Haoxiang Jiang, Lincan Li +5

Fine-tuning large pre-trained foundation models often yields excellent downstream performance but is prohibitively expensive when updating all parameters. Parameter-efficient fine-…