Publications

Orthrus: Memory-Efficient Parallel Token Generation via Dual-View Diffusion

Chien Van Nguyen, Chaitra Hegde, Van Cuong Pham, Ryan A. Rossi, Franck Dernoncourt, Thien Huu Nguyen

Spotlight paper

Hallucinate at the Last in Long Response Generation: A Case Study on Long Document Summarization

Joonho_Yang, David Seunghyun Yoon, Hwan Chang, Byeongjeong Kim, Hwanhee Lee

CRISP: Cliff-aware Residual-free Input-adaptive Sparse Prefilling with Entropy-Motivated Routing

Huy Huu Nguyen, Chien Van Nguyen, Franck Dernoncourt, Ryan A. Rossi, Linh Ngo Van, Jieyang Chen, Thien Huu Nguyen

EventKD: Event-Aware Knowledge Distillation for Generative Event Extraction

Hoang Thanh Dat, Quoc Phong Dao, Nam Le Hai, Franck Dernoncourt, Linh Ngo Van, Trung Le, Thien Huu Nguyen

GRASP: GRanularity-Aware Search Policy for Agentic RAG

Varun Gandhi, Jaewook Lee, Shantanu Todmal, Franck Dernoncourt, Ryan A. Rossi, Jack Wang, Andrew Lan

Not Worth Another Token: Marginal Value Estimation for Efficient Deep Research Agents

Harshitha Kolukuluru, Reshma Ashok, Kirat Arora, Evan William Ciccarelli, Nischal Ashok Kumar, Lunyiu Nie, Franck Dernoncourt, Samyadeep Basu, Ryan A. Rossi, Nedim Lipka

Trust but Verify: Introducing DAVinCI – A Framework for Dual Attribution and Verification in Claim Inference for Language Models

Vipula Rawte, Ryan A. Rossi, Franck Dernoncourt, Nedim Lipka

Code-Switching Reveals Language Anchoring in Multilingual LLMs

Jeonghyun Park, David Seunghyun Yoon, Yonghyun Jun, Hwanhee Lee

CHARM: Character Hallucination for Multicultural Role Play Benchmark

Sunkyung_Han, Nahyeon Park, Gaeun Seo, David Seunghyun Yoon, JinYeong Bak

Reward-Validated Coactive Learning for Stylized Slide Design

Avijit Dasgupta, Joseph K J, Pannaga Shivaswamy, Sunandini Sanyal, Sambaran Bandyopadhyay, Sayan Nag, Balaji Vasan Srinivasan, CV Jawahar, Karteek Alahari