6 citations · 17 across the 32 of their papers we have counts for
14 papers · 1 filter
SliderEdit++: Improved Slider Trajectories in Instruction-Based Image Editing
Arman Zarei, Sayan Nag, Bryan Wang +5
Slider-based control aims to give users continuous, fine-grained control over the intensity of individual edits in instruction-based image editing. However, existing approaches fai…
Personalized Image Generation with Reasoning and Reflection
Bo Ni, Ngoc N. Tran, Qinwen Ge +10
Personalized image generation has remained narrowly focused on conditional synthesis from curated visual exemplars, rather than capturing who a user is. In practice, however, a use…
FlexRouter: Learning Complementary Model Sets for Flexible LLM Routing
Wang Wei, Harry Yang, Tiankai Yang +6
Existing Large Language Model (LLM) routing methods score LLMs independently to select top- models. However, this ignores model correlations and enforces a rigid computational b…
Beyond Top- Skill Retrieval: Diversity-Aware Skill Routing for LLM Agents
Wang Wei, Tiankai Yang, Samyadeep Basu +7
Large language model (LLM) agents increasingly rely on external skills, but routing user requests over large skill registries is difficult because many skills are functionally redu…
Spurious Advantage Hidden in GRPO
Jiamian Wang, Samyadeep Basu, Koustava Goswami +2
Group Relative Policy Optimization (GRPO) is widely studied for reinforcement learning with verifiable rewards, where its advantage estimator assigns each rollout a magnitude from…
A Glance Is All You Need: Single-Pass Fine-Grained Image Captioning with SimLoss
Suryaansh Jain, Rahasya Barkur, Vishal G +8
An image may be worth a thousand words, but most captioning models describe it in only a few. Modern vision-language models produce fluent high-level captions, yet routinely miss t…
Not Worth Another Token: Marginal Value Estimation for Efficient Deep Research Agents
Harshitha Kolukuluru, Reshma Ashok, Kirat Arora +7
Long-horizon research agents solve open-ended tasks through iterative retrieval, aggregation, and synthesis, but context grows rapidly while the marginal value of additional eviden…
KnowSim: Evaluating Information Calibration in LLM Assistants with User Simulators that Learn
Yoonjoo Lee, Hyoungwook Jin, Tae Soo Kim +3
To effectively collaborate with users on knowledge-intensive tasks, Large Language Models (LLMs) must perform information calibration: matching content to a user's evolving underst…
MultAttnAttrib: Training-Free Multimodal Attribution in Long Document Question Answering
Dang Quang Thien Tran, Quang V. Dang, Vinamra Tyagi +7
As grounded QA systems are increasingly deployed in AI assistants, accurately attributing generated answers to evidence is critical for user trust and model safety. While unimodal…
DocArena: Turning Raw Documents into Controllable Training Environments for Document Search Agents
Jiamian Wang, Ruiyi Zhang, Tong Yu +5
Recent methods train search agents via reinforcement learning from (question, answer, evidence) tuples without requiring expert trajectories. The tuples serve as the training envir…
Sparse Personalized Text Generation with Multi-Trajectory Reasoning
Bo Ni, Haowei Fu, Qinwen Ge +10
As Large Language Models (LLMs) advance, personalization has become a key mechanism for tailoring outputs to individual user needs. However, most existing methods rely heavily on d…
A Survey on LLM-based Conversational User Simulation
Bo Ni, Leyao Wang, Yu Wang +27
User simulation has long played a vital role in computer science due to its potential to support a wide range of applications. Language, as the primary medium of human communicatio…
Human-Aligned MLLM Judges for Fine-Grained Image Editing Evaluation: A Benchmark, Framework, and Analysis
Runzhou Liu, Hailey Weingord, Sejal Mittal +18
Evaluating image editing models remains challenging due to the coarse granularity and limited interpretability of traditional metrics, which often fail to capture aspects important…
Reasoning-Based Personalized Generation for Users with Sparse Data
Bo Ni, Branislav Kveton, Samyadeep Basu +14
Large Language Model (LLM) personalization holds great promise for tailoring responses by leveraging personal context and history. However, real-world users usually possess sparse…