Institution profile

University of California, Los Angeles

Academic institutionnorthamerica · us
Official website
Research library1,722linked papers
Opportunities0open roles
Selected work

Representative Papers

SparseGS: Real-Time 360{deg} Sparse View Synthesis using Gaussian Splatting

Nov 30, 2023

This work addresses the severe degradation in 3D Gaussian Splatting (3DGS) reconstruction quality under sparse training views (only 3–12 images), manifesting as “floating artifacts” and “background collapse” in unseen viewpoints. To tackle this, we propose a depth-prior-guided optimization framework. Our key contributions are: (1) a geometry-aware depth prior derived from monocular depth estimation, enforcing spatial plausibility of Gaussian distributions; (2) an unseen-view regularization module that explicitly enhances generalization under sparse view coverage; and (3) an adaptive joint geometry-density pruning strategy to improve reconstruction compactness and stability. Integrating differentiable Gaussian rendering, depth-guided optimization, and viewpoint-aware regularization, our method achieves state-of-the-art performance on Mip-NeRF360, LLFF, and DTU benchmarks—reaching top-tier forward-facing scene quality using only three input images, with efficient training and real-time inference.

63 citations5 influentialRead paper

IdealGPT: Iteratively Decomposing Vision and Language Reasoning via Large Language Models

May 24, 2023Conference on Empirical Methods in Natural Language Processing

Existing vision-language models (VLMs) exhibit limited performance on zero-shot multi-step reasoning tasks, primarily due to their reliance on domain-specific subproblem decomposers and their tendency to force final answers even under insufficient information—compromising reasoning reliability. This paper proposes the first domain-agnostic, adaptive iterative decomposition framework: an LLM first generates subquestions; a VLM then provides visually grounded subanswers via multimodal grounding; finally, the LLM aggregates results and dynamically decides whether to terminate. This enables trustworthy, self-correcting convergence. The framework integrates zero-shot prompting synergy with a divide-and-conquer architecture, substantially enhancing reasoning robustness. Under zero-shot settings, it achieves absolute accuracy gains of +10.2% and +15.6% over the strongest GPT-4–based baselines on the VCR and SNLI-VE benchmarks, respectively.

42 citations6 influentialRead paper

SAT-MapIt: A SAT-based Modulo Scheduling Mapper for Coarse Grain Reconfigurable Architectures

Apr 01, 2023Design, Automation and Test in Europe

This paper addresses the efficient mapping of compute-intensive loops onto coarse-grained reconfigurable arrays (CGRAs), targeting minimization of the initiation interval (II). We propose a SAT-based modulo scheduling approach, whose core innovation is Kernel Movement Scheduling (KMS)—a novel scheduling representation that uniformly encodes mapping constraints as Boolean logic formulas, thereby overcoming the search limitations inherent in conventional graph-based algorithms. Integrating modulo scheduling theory, dataflow graph analysis, and iterative feasibility verification, our method systematically generates and validates legal mappings for a given II. Experimental evaluation demonstrates that our approach outperforms state-of-the-art techniques on 47.72% of benchmarks, achieving lower IIs and uncovering several previously unrecognized valid mappings.

13 citationsRead paper

The Cost of Optimally Acquired Information

Nov 07, 2025

This paper addresses the optimization challenge in modeling information acquisition costs. Methodologically, it proposes a sequential information acquisition framework grounded in cost minimization and introduces the novel concept of “sequential learning resistance.” Integrating sequential decision theory, convex analysis, and dynamic programming, the framework constructs and solves a recursive structure for the indirect cost function, enabling a rigorous transformation from direct to computationally tractable indirect costs. Theoretically, it establishes the first optimization foundation for “uniformly posterior-separable” costs and uncovers a fundamental trade-off—previously implicit in the rational inattention literature—between information sensitivity and computational feasibility. Practically, it constructs two new classes of indirect cost functions that are both analytically tractable and economically interpretable, substantially enhancing the model’s applicability in empirical work and policy analysis.

12 citations2 influentialRead paper
Recent publications

Latest Papers