Institution profile

University of Central Florida

Academic institutionnorthamerica · us
Official website
Research library721linked papers
Opportunities0open roles
Selected work

Representative Papers

Sports-QA: A Large-Scale Video Question Answering Benchmark for Complex and Professional Sports

Jan 03, 2024arXiv.org

Existing VideoQA datasets lack fine-grained modeling of professional sports actions, hindering effective reasoning for descriptive, temporal, causal, and counterfactual questions. To address this, we introduce Sports-QA—the first video question answering benchmark tailored to professional sports scenarios—covering multiple sports disciplines and four categories of complex reasoning tasks. Methodologically, we propose the Auto-Focus Transformer (AFT), which employs an attention-driven dynamic focusing mechanism to adaptively model multi-scale temporal information and integrates joint video–language representation learning. Extensive experiments demonstrate that AFT achieves state-of-the-art performance on Sports-QA, substantially outperforming general-purpose VideoQA models. This work constitutes the first systematic validation of an architecture explicitly designed for fine-grained sports action understanding and dynamic logical reasoning, establishing a new foundation for domain-specific VideoQA research.

10 citations2 influentialRead paper

Draft-Conditioned Constrained Decoding for Structured Generation in LLMs

Feb 08, 2026arXiv.org

This work addresses the semantic drift often induced by hard constraints in structured generation, where conventional constrained decoding—while ensuring syntactic validity—can yield outputs that are locally well-formed yet semantically incorrect. To mitigate this issue, the authors propose a training-free, two-stage inference framework: first generating an unconstrained semantic draft, then performing constraint-aware decoding conditioned on this draft to decouple semantics from structure. By conditioning on the draft, the method alleviates the distributional shift caused by rigid constraints and optionally incorporates a multi-draft selection mechanism to further enhance output quality. Evaluated on benchmarks such as GSM8K, the approach improves structured accuracy by up to 24 percentage points (from 15.2% to 39.0%), demonstrating that ensembles of smaller models using this strategy can outperform larger models relying on traditional constrained decoding baselines.

5 citationsRead paper

Exploration of Unary Arithmetic-Based Matrix Multiply Units for Low Precision DL Accelerators

Jul 01, 2024IEEE Computer Society Annual Symposium on VLSI

This work evaluates the energy efficiency and performance potential of unary arithmetic for matrix multiplication (GEMM) in low-precision deep learning accelerators. It presents the first rigorous post-synthesis hardware assessment of three state-of-the-art unary GEMM architectures—uGEMM, tuGEMM, and tubGEMM—systematically analyzing their behavior across varying bit widths, matrix dimensions, and realistic weight sparsity patterns from actual models, including CNNs and LLaMA2. The results demonstrate that, under specific configurations, unary GEMM can significantly outperform conventional binary designs, offering a promising high-efficiency computing paradigm for edge AI inference and clearly delineating its optimal application scenarios.

3 citationsRead paper

LoL: Longer than Longer, Scaling Video Generation to Hour

Jan 23, 2026

This work addresses the "sink frame collapse" phenomenon in autoregressive long-video generation, where excessive reliance on specific sink frames by attention mechanisms leads to abrupt scene transitions and repetitive motion patterns. To mitigate this issue without retraining, the authors propose a lightweight intervention: injecting random perturbations into the rotary positional embeddings (RoPE) within multi-head attention layers. This simple modification effectively breaks the homogeneity across attention heads, thereby suppressing sink frame collapse. The method enables real-time, streaming video generation of unlimited length while maintaining high visual fidelity. In public demonstrations, it successfully produced a continuous 12-hour video—the longest streaming-generation result reported to date—with minimal quality degradation over time.

2 citationsRead paper

Learning Latency-Aware Orchestration for Parallel Multi-Agent Systems

Jan 15, 2026

This work addresses the high latency in multi-agent systems caused by multi-step reasoning and redundant agent invocations during parallel execution, which often fails to meet real-time requirements. To this end, the authors propose LAMaS, a novel framework that introduces explicit latency supervision signals into multi-agent orchestration for the first time. LAMaS employs a learning-driven controller to construct an execution topology graph and leverages critical path analysis to optimize parallel scheduling. This approach departs from conventional paradigms centered on task performance or cost, instead prioritizing latency reduction along the critical path. Experimental results demonstrate that LAMaS reduces critical path length by 38%–46% compared to state-of-the-art methods across multiple benchmarks, while maintaining or even improving task performance.

1 citationsRead paper
Recent publications

Latest Papers