47 citations · 60 across the 36 of their papers we have counts for
36 papers
Seeing the End at Step Zero: Accelerating Diffusion MLLMs via MLP Sparsity-Aware Truncation
Qicheng Zhao, Qi Sun, Zheyu Yan
Diffusion Multimodal Large Language Models (DMLLMs) are highly effective for multimodal reasoning, yet their inference efficiency is significantly hindered by fixed-length generati…
ResilPhase: Plug-and-Play Phase Mapping and Noise-Resilient Macro-Trajectory Extrapolation for Diffusion Acceleration
Qicheng Zhao, Yu Li, Qi Sun +1
The adoption of powerful diffusion models is hindered by their significant inference latency. Recent ``cache-then-forecast'' schemes alleviate this issue by accelerating DiTs using…
Sakana Fugu Technical Report
Yujin Tang, Edoardo Cetin, Jinglue Xu +11
The capabilities of frontier Large Language Models (LLMs) continue to advance, with different providers increasingly specializing in distinct domains. This raises a natural next ob…
From "Weak" Signals to Strong Models: Preference Delta Aggregation with LoRA Merging
Qi Sun, Siyue Zhang, Yulin Chen +3
Training strong large language models (LLMs) requires high-quality supervision, which is often scarce. Recent work shows that paired preference data from weak-weaker model pairs (e…
QueryAgent-R1: Bridging Query Generation and Product Retrieval for E-Commerce Query Recommendation
Dike Sun, Zheng Zou, Jingtong Zang +3
Query recommendation in e-commerce search aims to proactively suggest queries that match users' potential interests. However, existing methods mainly optimize query-level relevance…
Privy: From Fine Print to Fair Practice in Privacy Rights Exercise
Qi Sun, Ziyang Li, Yinzhi Cao +1
Privacy regulations such as the CCPA and GDPR grant individuals rights over their personal data, yet it remains challenging for most users to exercise them in practice due to vague…
FSFM: A Biologically-Inspired Framework for Selective Forgetting of Agent Memory
Yingjie Gu, Wenjian Xiong, Liqiang Wang +7
For LLM agents, memory management critically impacts efficiency, quality, and security. While much research focuses on retention, selective forgetting--inspired by human cognitive…
Search, Do not Guess: Teaching Small Language Models to Be Effective Search Agents
Yizhou Liu, Qi Sun, Yulin Chen +2
Agents equipped with search tools have emerged as effective solutions for knowledge-intensive tasks. While Large Language Models (LLMs) exhibit strong reasoning capabilities, their…
Quality Over Clicks: Iterative Reinforcement Learning for Early-Stage E-Commerce Query Suggestion
Qi Sun, Kejun Xiao, Huaipeng Zhao +2
Existing dialogue systems rely on query suggestion to enhance user engagement. Recent approaches mainly optimize generative models using click-through rate (CTR) models to align wi…
Evolutionary Context Search for Automated Skill Acquisition
Qi Sun, Stefan Nielsen, Rio Yokota +1
Large Language Models cannot reliably acquire new knowledge post-deployment -- even when relevant text resources exist, models fail to transform them into actionable knowledge with…
IGMiRAG: Intuition-Guided Retrieval-Augmented Generation with Adaptive Mining of In-Depth Memory
Xingliang Hou, Yuyan Liu, Qi Sun +4
Retrieval-augmented generation (RAG) equips large language models (LLMs) with reliable knowledge memory. To strengthen cross-text associations, recent research integrates graphs an…
Atomic Information Flow: A Network Flow Model for Tool Attributions in RAG Systems
James Gao, Josh Zhou, Qi Sun +2
Many tool-based Retrieval Augmented Generation (RAG) systems lack precise mechanisms for tracing final responses back to specific tool components -- a critical gap as systems scale…
Beyond Crash: Hijacking Your Autonomous Vehicle for Fun and Profit
Qi Sun, Ahmed Abdo, Luis Burbano +4
Autonomous Vehicles (AVs), especially vision-based AVs, are rapidly being deployed without human operators. As AVs operate in safety-critical environments, understanding their robu…
Orchestrating Specialized Agents for Trustworthy Enterprise RAG
Xincheng You, Qi Sun, Neha Bora +4
Retrieval-Augmented Generation (RAG) shows promise for enterprise knowledge work, yet it often underperforms in high-stakes decision settings that require deep synthesis, strict tr…
MaDiS: Taming Masked Diffusion Language Models for Sign Language Generation
Ronglai Zuo, Rolandos Alexandros Potamias, Qi Sun +3
Sign language generation (SLG) aims to translate written texts into expressive sign motions, bridging communication barriers for the Deaf and Hard-of-Hearing communities. Recent st…
TRINITY: An Evolved LLM Coordinator
Jinglue Xu, Qi Sun, Peter Schwendeman +3
Combining diverse foundation models is promising, but weight-merging is limited by mismatched architectures and closed APIs. Trinity addresses this with a lightweight coordinator t…
Learning to Orchestrate Agents in Natural Language with the Conductor
Stefan Nielsen, Edoardo Cetin, Peter Schwendeman +3
Powerful large language models (LLMs) from different providers have been expensively trained and finetuned to specialize across varying domains. In this work, we introduce a new ki…
OregairuChar: A Benchmark Dataset for Character Appearance Frequency Analysis in My Teen Romantic Comedy SNAFU
Qi Sun, Dingju Zhou, Lina Zhang
The analysis of character appearance frequency is essential for understanding narrative structure, character prominence, and story progression in anime. In this work, we introduce…
CHAI: Command Hijacking against embodied AI
Luis Burbano, Diego Ortiz, Qi Sun +5
Embodied Artificial Intelligence (AI) promises to handle edge cases in robotic vehicle systems where data is scarce by using common-sense reasoning grounded in perception and actio…
Towards Robust Agentic CUDA Kernel Benchmarking, Verification, and Optimization
Robert Tjarko Lange, Qi Sun, Aaditya Prasad +3
Recent advances in large language models (LLMs) demonstrate their effectiveness in scaling test-time compute for software engineering tasks. However, these approaches often focus o…
ShoppingBench: A Real-World Intent-Grounded Shopping Benchmark for LLM-based Agents
Jiangyuan Wang, Kejun Xiao, Qi Sun +4
Existing benchmarks in e-commerce primarily focus on basic user intents, such as finding or purchasing products. However, real-world users often pursue more complex goals, such as…
Advancing Sequential Numerical Prediction in Autoregressive Models
Xiang Fei, Jinghui Lu, Qi Sun +6
Autoregressive models have become the de facto choice for sequence generation tasks, but standard approaches treat digits as independent tokens and apply cross-entropy loss, overlo…
From Grounding to Manipulation: Case Studies of Foundation Model Integration in Embodied Robotic Systems
Xiuchao Sui, Daiying Tian, Qi Sun +4
Foundation models (FMs) are increasingly used to bridge language and action in embodied agents, yet the operational characteristics of different FM integration strategies remain un…
NORA: A Small Open-Sourced Generalist Vision Language Action Model for Embodied Tasks
Chia-Yu Hung, Qi Sun, Pengfei Hong +5
Existing Visual-Language-Action (VLA) models have shown promising performance in zero-shot scenarios, demonstrating impressive task execution and reasoning capabilities. However, a…