Selected work

Representative Papers

Inject or Navigate? Token-Efficient Retrieval for LLM Analysis of Transactional Legal Documents

Jul 06, 2026

This study addresses the challenge of high token consumption and performance degradation in transactional legal document question answering when naively injecting entire corpora into large language models. The authors propose a structure-aware chunking strategy and comparatively evaluate three approaches: full corpus injection, embedding-based retrieval (NAVEMBED), and a novel large model navigation framework leveraging a compact structural index (NAVINDEX). NAVINDEX introduces an innovative navigation mechanism coupled with a cached intersection cost model, achieving substantial reductions in token usage—1.61× fewer total tokens and a 56× smaller context window—alongside a 25% cost reduction, while maintaining answer quality on par with full injection. Experimental results show that NAVEMBED matches full injection on 16 out of 18 tasks with 17.3× fewer tokens, whereas NAVINDEX consistently matches performance across all tasks, demonstrating superior efficiency and cost-effectiveness.

0 citationsRead paper

Pixel3DMM: Versatile Screen-Space Priors for Single-Image 3D Face Reconstruction

May 01, 2025

This paper addresses high-fidelity 3D face reconstruction from a single RGB image. We propose Pixel3DMM, a vision transformer leveraging DINO features that regresses surface normals and UV coordinates pixel-wise, enabling differentiable optimization of FLAME parameters. Our method introduces the first screen-space geometric prior mechanism and establishes the first large-scale benchmark for single-image reconstruction—covering diverse expressions, poses, and ethnicities (976K images across 1,000+ identities)—which uniquely supports joint geometric accuracy evaluation under both neutral and dynamic expressions. On this benchmark, Pixel3DMM reduces geometric error by over 15% compared to the strongest baseline, significantly improving reconstruction fidelity for posed expressions and enhancing cross-pose and cross-expression generalization.

0 citationsRead paper

Recent publications

Latest Papers

Inject or Navigate? Token-Efficient Retrieval for LLM Analysis of Transactional Legal Documents

Jul 06, 2026

This study addresses the challenge of high token consumption and performance degradation in transactional legal document question answering when naively injecting entire corpora into large language models. The authors propose a structure-aware chunking strategy and comparatively evaluate three approaches: full corpus injection, embedding-based retrieval (NAVEMBED), and a novel large model navigation framework leveraging a compact structural index (NAVINDEX). NAVINDEX introduces an innovative navigation mechanism coupled with a cached intersection cost model, achieving substantial reductions in token usage—1.61× fewer total tokens and a 56× smaller context window—alongside a 25% cost reduction, while maintaining answer quality on par with full injection. Experimental results show that NAVEMBED matches full injection on 16 out of 18 tasks with 17.3× fewer tokens, whereas NAVINDEX consistently matches performance across all tasks, demonstrating superior efficiency and cost-effectiveness.

0 citationsRead paper

Pixel3DMM: Versatile Screen-Space Priors for Single-Image 3D Face Reconstruction

May 01, 2025

This paper addresses high-fidelity 3D face reconstruction from a single RGB image. We propose Pixel3DMM, a vision transformer leveraging DINO features that regresses surface normals and UV coordinates pixel-wise, enabling differentiable optimization of FLAME parameters. Our method introduces the first screen-space geometric prior mechanism and establishes the first large-scale benchmark for single-image reconstruction—covering diverse expressions, poses, and ethnicities (976K images across 1,000+ identities)—which uniquely supports joint geometric accuracy evaluation under both neutral and dynamic expressions. On this benchmark, Pixel3DMM reduces geometric error by over 15% compared to the strongest baseline, significantly improving reconstruction fidelity for posed expressions and enhancing cross-pose and cross-expression generalization.

0 citationsRead paper