27 citations · 46 across the 13 of their papers we have counts for
13 papers
What the Reranker Sees: Multi-Aspect Page Annotation for Long-Document Multimodal Question Answering
Guanchen Wu, Jiayuan Ding, Subhabrata Mukherjee +1
Long-document visual question answering (VQA) over documents of tens to hundreds of pages mixing text, tables, charts, and figures typically follows retrieve-then-read pipelines. I…
MatrAIx: Simulating the World with 8.3 Billion Persona Agents
Xiaomin Li, Yuexing Hao, Jianheng Hou +90
Human evaluation of AI systems and digital products is costly, slow, and difficult to scale. Offline evaluations are more scalable but often abstract away human diversity and inter…
Agents' Last Exam
Yiyou Sun, Xinyang Han, Weichen Zhang +378
Recent AI systems have achieved strong results on a wide range of benchmarks, yet these gains have not translated into economically meaningful deployment across many professional d…
A Simple Plug-in for Improving Eviction-Based KV Cache Compression
Yuping Lin, Jiayuan Ding, Yue Xing +3
KV cache growth is a major bottleneck for long-context inference in large language models. Existing methods are often dominated by binary eviction or representation approximation,…
LMM-Track4D: Eliciting 4D Dynamic Reasoning in LMMs via Trajectory-Grounded Dialogue
Chaoyue Li, Yongxue Xu, Jie Feng +1
Recent large multimodal models (LMMs) have become increasingly capable on image and video understanding, yet still struggle to sustain 4D continuous spatiotemporal dynamic reasonin…
Crafting Reversible SFT Behaviors in Large Language Models
Yuping Lin, Pengfei He, Yue Xing +5
Supervised fine-tuning (SFT) induces new behaviors in large language models, yet imposes no structural constraint on how these behaviors are distributed within the model. Existing…
VISD: Enhancing Video Reasoning via Structured Self-Distillation
Hao Lin, Kunyang Lv, Xu Jiang +5
Training VideoLLMs for complex reasoning remains challenging due to sparse sequence level rewards and the lack of fine grained credit assignment over long, temporally grounded reas…
Perfecting Human-AI Interaction at Clinical Scale. Turning Production Signals into Safer, More Human Conversations
Subhabrata Mukherjee, Markel Sanz Ausin, Kriti Aggarwal +24
Healthcare conversational AI agents shouldn't be optimized only for clean benchmark accuracy in production-first regime; they must be optimized for the lived reality of patient con…
TRAJECT-Bench:A Trajectory-Aware Benchmark for Evaluating Agentic Tool Use
Pengfei He, Zhenwei Dai, Bing He +10
Large language model (LLM)-based agents increasingly rely on tool use to complete real-world tasks. While existing works evaluate the LLMs' tool use capability, they largely focus…
GraphGhost: Tracing Structures Behind Large Language Models
Xinnan Dai, Xianxuan Long, Chung-Hsiang Lo +4
Large Language Models (LLMs) exhibit strong reasoning capabilities on structured tasks, yet the internal mechanisms underlying such behaviors remain poorly understood. Existing int…
MIXRAG : Mixture-of-Experts Retrieval-Augmented Generation for Textual Graph Understanding and Question Answering
Lihui Liu, Jiayuan Ding, Subhabrata Mukherjee +1
Large Language Models (LLMs) have achieved impressive performance across a wide range of applications. However, they often suffer from hallucinations in knowledge-intensive domains…
Retrieval-Augmented Generation with Graphs (GraphRAG)
Haoyu Han, Yu Wang, Harry Shomer +15
Retrieval-augmented generation (RAG) is a powerful technique that enhances downstream task execution by retrieving additional information, such as knowledge, skills, and tools from…
Polaris: A Safety-focused LLM Constellation Architecture for Healthcare
Subhabrata Mukherjee, Paul Gamble, Markel Sanz Ausin +23
We develop Polaris, the first safety-focused LLM constellation for real-time patient-AI healthcare conversations. Unlike prior LLM works in healthcare focusing on tasks like questi…