Institution profile

Syracuse University

Academic institutionnorthamerica · us
Official website
Research library157linked papers
Opportunities0open roles
Selected work

Representative Papers

One-Bit Compressed Sensing Using Generative Models

May 01, 2020IEEE International Conference on Acoustics, Speech, and Signal Processing

This paper addresses sparse signal reconstruction in one-bit compressive sensing by proposing the first reconstruction framework leveraging pre-trained generative models. Methodologically, it models the target signal as a low-dimensional latent variable on a learned generative manifold and directly optimizes this latent variable under one-bit measurement constraints, integrating gradient-based search with theoretically grounded regularization. Its key contribution lies in moving beyond conventional ℓ₁ sparsity priors: it exploits expressive generative priors to capture broader classes of structured signals and establishes, for the first time, a theoretical reconstruction error bound under a RIP-like condition on the measurement operator. Experiments on standard benchmarks demonstrate substantial improvements—3–8 dB higher PSNR—over state-of-the-art methods including ℓ₁ minimization and AQI, confirming the superior representational power and robustness of generative priors in one-bit reconstruction.

6 citationsRead paper

Why Keep Your Doubts to Yourself? Trading Visual Uncertainties in Multi-Agent Bandit Systems

Jan 26, 2026

This work addresses the high coordination costs and low efficiency commonly encountered by multi-agent vision systems under information asymmetry, problems exacerbated by existing approaches that overlook the structural nature of uncertainty and lack economic sustainability. To this end, we propose Agora, a novel framework that formalizes epistemic uncertainty as a tradable asset and establishes a decentralized uncertainty market, wherein agents are incentivized through economic mechanisms to exchange uncertainty at the levels of perception, semantics, and reasoning. Agora integrates vision-language models with multi-armed bandits and Thompson Sampling to devise market-aware brokerage strategies. Experiments demonstrate that Agora significantly outperforms current methods across five multimodal benchmarks, achieving an 8.5% accuracy gain on MMMU while reducing coordination costs by more than threefold.

2 citationsRead paper

Asymptotically Optimal Quantum Universal Quickest Change Detection

Feb 03, 2026

This work addresses the problem of rapid change detection in quantum systems when the post-change state is unknown. The authors propose a two-stage approach: first, quantum information is converted into classical data via a block positive operator-valued measure (POVM) that preserves quantum relative entropy; then, a windowed CUSUM algorithm is applied to detect changes in the resulting classical sequence. This study represents the first extension of the classical universal quickest change detection framework to the quantum setting. Under the general assumption of an unknown post-change quantum state, the proposed method is proven to be asymptotically optimal in terms of worst-case average detection delay, thereby achieving a theoretical breakthrough and establishing performance optimality in quantum quickest change detection.

1 citations1 influentialRead paper

From We to Me: Theory Informed Narrative Shift with Abductive Reasoning

Feb 10, 2026arXiv.org

This study addresses the challenge large language models (LLMs) face in preserving both semantic fidelity and narrative coherence during cross-cultural narrative transfer, particularly when shifting between collectivist and individualist frameworks. To overcome this limitation, the authors propose a neuro-symbolic approach that integrates sociological narrative theory with abductive reasoning, enabling interpretable and high-fidelity cross-cultural narrative adaptation. The method automatically extracts narrative rules to guide LLMs in goal-directed transformation. Experimental results demonstrate a 55.88% improvement in narrative transfer performance on GPT-4o, a 40.4% enhancement in semantic fidelity (measured by KL divergence), and consistently superior outcomes across mainstream models including Llama-4, Grok-4, and Deepseek-R1, substantially surpassing the zero-shot transfer capabilities of current LLMs.

1 citationsRead paper

Automatic Reward Shaping from Confounded Offline Data

May 16, 2025

This work addresses offline reinforcement learning under unobserved confounding, where input mismatch between behavior and target policies induces biased policy evaluation. We propose the first deep RL algorithm that integrates worst-case environmental robustness into the offline DQN framework. Our method unifies causal counterfactual robust optimization with minimax policy search, yielding a provably safe reward shaping technique that requires neither observability of confounders nor domain-specific priors. Evaluated on 12 confounded Atari benchmarks, our approach consistently outperforms standard DQN—achieving 37%–62% gains in policy performance under severe input mismatch. The framework establishes a new paradigm for safe and reliable offline policy learning in high-dimensional, nonstationary environments.

1 citationsRead paper
Recent publications

Latest Papers