4 citations · 16 across the 27 of their papers we have counts for
31 papers
Can Agent Harnesses and Inference Engines Hear Each Other? The HEAR Protocol for Agentic LLM Serving
Jiaqi Zhao, Haodong Chen, Jitai Hao +4
LLM agents increasingly execute complex workflows involving multi-turn reasoning, tool use, and parallel agents. Efficient serving requires decisions that span two layers with comp…
SparseEngine: Sparse-First Inference Engine
Jitai Hao, Quansheng Gu, Qiang Huang +1
Long-context LLM agents accumulate interaction histories that strain KV-cache memory and attention computation. Although sparse attention reduces these costs, heterogeneous cache r…
ShallowStream: Index Shallow then Answer Deep for Streaming Video Understanding
Jitai Hao, Ke Yang, Qiang Huang +3
Streaming video understanding is a critical capability for real-world applications, including embodied intelligence, autonomous driving, industrial monitoring, surveillance and ear…
Weight-Informed Self-Explaining Clustering for Mixed-Type Tabular Data
Lehao Li, Qiang Huang, Yihao Ang +3
Clustering mixed-type tabular data is fundamental for exploratory analysis, yet remains challenging due to misaligned numerical-categorical representations, uneven and context-depe…
MG-RAG: Multi-Granularity Graph for Multimodal Retrieval-Augmented Generation
Sijun Dai, Qiang Huang, Xiaoxing You +1
Retrieval-Augmented Generation (RAG) mitigates hallucinations in Multimodal Large Language Models (MLLMs), yet existing systems struggle with complex cross-modal reasoning. Flat ve…
Cut to the Chase: Training-free Multimodal Summarization via Chain-of-Events
Xiaoxing You, Qiang Huang, Lingyu Li +2
Multimodal Summarization (MMS) aims to generate concise textual summaries by understanding and integrating information across videos, transcripts, and images. However, existing app…
ResidualKV: Residual-Based KV Cache Compression for Efficient Long-Context Inference
Jitai Hao, Qiang Huang, Yaowei Wang +2
Efficient long-context inference faces two coupled bottlenecks: KV-cache memory grows linearly with context length, while attention computation grows quadratically. Existing approa…
When Abundance Conceals Weakness: Knowledge Conflict in Multilingual Models
Jiaqi Zhao, Qiang Huang, Haodong Chen +2
Large Language Models (LLMs) encode vast world knowledge across multiple languages, yet their internal beliefs are often unevenly distributed across linguistic spaces. When externa…
Measuring Social Bias in Vision-Language Models with Face-Only Counterfactuals from Real Photos
Haodong Chen, Qiang Huang, Jiaqi Zhao +3
Vision-Language Models (VLMs) are increasingly deployed in socially consequential settings, raising concerns about social bias driven by demographic cues. A central challenge in me…
IDRBench: Benchmarking the Interactive Capabilities of Deep Research Agents
Yingchaojie Feng, Qiang Huang, Xiaoya Xie +4
Large Language Model (LLM)-based deep research agents perform multi-step reasoning, web exploration, and long-form report generation. In these long-horizon workflows, early deviati…
One Swallow Does Not Make a Summer: Understanding Semantic Structures in Embedding Spaces
Yandong Sun, Qiang Huang, Ziwei Xu +3
Embedding spaces are fundamental to modern AI, translating raw data into high-dimensional vectors that encode rich semantic relationships. Yet, their internal structures remain opa…
Partially Shared Concept Bottleneck Models
Delong Zhao, Qiang Huang, Di Yan +2
Concept Bottleneck Models (CBMs) enhance interpretability by introducing a layer of human-understandable concepts between inputs and predictions. While recent methods automate conc…
Knowledge Completes the Vision: A Multimodal Entity-aware Retrieval-Augmented Generation Framework for News Image Captioning
Xiaoxing You, Qiang Huang, Lingyu Li +4
News image captioning aims to produce journalistically informative descriptions by combining visual content with contextual cues from associated articles. Despite recent advances,…
RFOD: Random Forest-based Outlier Detection for Tabular Data
Yihao Ang, Peicheng Yao, Yifan Bao +4
Outlier detection in tabular data is crucial for safeguarding data integrity in high-stakes domains such as cybersecurity, financial fraud detection, and healthcare, where anomalie…
Uni-X: Mitigating Modality Conflict with a Two-End-Separated Architecture for Unified Multimodal Models
Jitai Hao, Hao Liu, Xinyan Xiao +2
Unified Multimodal Models (UMMs) built on shared autoregressive (AR) transformers are attractive for their architectural simplicity. However, we identify a critical limitation: whe…
CTBench: Cryptocurrency Time Series Generation Benchmark
Yihao Ang, Qiang Wang, Qiang Huang +5
Synthetic time series are essential tools for data augmentation, stress testing, and algorithmic prototyping in quantitative finance. However, in cryptocurrency markets, characteri…
Position: Text Embeddings Should Capture Implicit Semantics, Not Just Surface Meaning
Yiqun Sun, Qiang Huang, Anthony K. H. Tung +1
This position paper argues that text embedding research should move beyond surface meaning and embrace implicit semantics as a central modeling objective. Text embeddings are a fou…
Don't Reinvent the Wheel: Efficient Instruction-Following Text Embedding based on Guided Space Transformation
Yingchaojie Feng, Yiqun Sun, Yandong Sun +4
In this work, we investigate an important task named instruction-following text embedding, which generates dynamic text embeddings that adapt to user instructions, highlighting spe…
PRISM: A Framework for Producing Interpretable Political Bias Embeddings with Political-Aware Cross-Encoder
Yiqun Sun, Qiang Huang, Anthony K. H. Tung +1
Semantic Text Embedding is a fundamental NLP task that encodes textual content into vector representations, where proximity in the embedding space reflects semantic similarity. Whi…
A Token is Worth over 1,000 Tokens: Efficient Knowledge Distillation through Low-Rank Clone
Jitai Hao, Qiang Huang, Hao Liu +3
Training high-performing Small Language Models (SLMs) remains costly, even with knowledge distillation and pruning from larger teacher models. Existing work often faces three key c…
A General Framework for Producing Interpretable Semantic Text Embeddings
Yiqun Sun, Qiang Huang, Yixuan Tang +2
Semantic text embedding is essential to many tasks in Natural Language Processing (NLP). While black-box models are capable of generating high-quality embeddings, their lack of int…
Towards Controllable Time Series Generation
Yifan Bao, Yihao Ang, Qiang Huang +2
Time Series Generation (TSG) has emerged as a pivotal technique in synthesizing data that accurately mirrors real-world time series, becoming indispensable in numerous applications…
Diversity-Aware -Maximum Inner Product Search Revisited
Qiang Huang, Yanhao Wang, Yiqun Sun +1
The -Maximum Inner Product Search (MIPS) serves as a foundational component in recommender systems and various data mining tasks. However, while most existing MIPS approac…
From Zero to Hero: Detecting Leaked Data through Synthetic Data Injection and Model Querying
Biao Wu, Qiang Huang, Anthony K. H. Tung
Safeguarding the Intellectual Property (IP) of data has become critically important as machine learning applications continue to proliferate, and their success heavily relies on th…