collaborators

5 papers

cs.LG2026

CORE: Context-Robust Remasking for Diffusion Language Models

Kevin Zhai, Sabbir Mollah, Zhenyi Wang +1

Standard decoding in Masked Diffusion Models (MDMs) is hindered by context rigidity: tokens are retained based on transient high confidence, often ignoring that early predictions l…

cs.CV2026

Curriculum-DPO++: Direct Preference Optimization via Data and Model Curricula for Text-to-Image Generation

Florinel-Alin Croitoru, Vlad Hondru, Radu Tudor Ionescu +2

Direct Preference Optimization (DPO) has been proposed as an effective and efficient alternative to reinforcement learning from human feedback (RLHF). However, neither RLHF nor DPO…

cs.CY2025

See, Think, Act: Online Shopper Behavior Simulation with VLM Agents

Yimeng Zhang, Jiri Gesi, Ran Xue +10

LLMs have recently demonstrated strong potential in simulating online shopper behavior. Prior work has improved action prediction by applying SFT on action traces with LLM-generate…

eess.IV2025

STROKEVISION-BENCH: A Multimodal Video And 2D Pose Benchmark For Tracking Stroke Recovery

David Robinson, Animesh Gupta, Rizwan Quershi +2

Despite advancements in rehabilitation protocols, clinical assessment of upper extremity (UE) function after stroke largely remains subjective, relying heavily on therapist observa…

cs.CL2025

Multi-Party Conversational Agents: A Survey

Sagar Sapkota, Mohammad Saqib Hasan, Mubarak Shah +1

Multi-party Conversational Agents (MPCAs) are systems designed to engage in dialogue with more than two participants simultaneously. Unlike traditional two-party agents, designing…