About

Pierre Liang is a Professor of Accounting at the Tepper School of Business at Carnegie Mellon University. His role involves teaching and research within the field of accounting, contributing to the academic community through his expertise. The Tepper School emphasizes experiential learning and practical application, preparing students to excel in their industries. As part of Carnegie Mellon University, Professor Liang is engaged in advancing knowledge in his field and supporting the school's strategic vision to lead at the intersection of business, technology, and analytics.

Research topics

• Artificial Intelligence
• Computer Science
• Psychology
• Machine Learning
• Natural Language Processing
• Computer Security
• Cognitive science
• Linguistics
• World Wide Web
• Database
• Data science

Selected publications

• Smell with Genji: Rediscovering Human Perception through an Olfactory Game with AI

  2026-04-13

  articleOpen access

  Olfaction plays an important role in human perception, yet its subjective and ephemeral nature makes it difficult to articulate, compare, and share across individuals. Traditional practices like the Japanese incense game Genji-kō offer one way to structure olfactory experience through shared interpretation. In this work, we present Smell with Genji, an artificial intelligence (AI)-mediated olfactory interaction system that reinterprets Genji-kō as a collaborative human-AI sensory experience. By integrating a game setup, a mobile application, and an AI co-smelling partner equipped with olfactory sensing and large language model (LLM)-based based conversational capabilities, the system invites participants to compare scents and construct Genji-mon patterns, fostering reflection through a dialogue that highlights the alignment and discrepancies between human and machine perception. This work illustrates how sensing-enabled AI can participate in olfactory experience alongside users, pointing toward new possibilities for AI-supported sensory interaction and reflection in human-computer interaction (HCI).

  PublisherDOI

• DENALI: A Dataset Enabling Non-Line-of-Sight Spatial Reasoning with Low-Cost LiDARs

  arXiv (Cornell University) · 2026-04-17

  articleOpen access

  Consumer LiDARs in mobile devices and robots typically output a single depth value per pixel. Yet internally, they record full time-resolved histograms containing direct and multi-bounce light returns; these multi-bounce returns encode rich non-line-of-sight (NLOS) cues that can enable perception of hidden objects in a scene. However, severe hardware limitations of consumer LiDARs make NLOS reconstruction with conventional methods difficult. In this work, we motivate a complementary direction: enabling NLOS perception with low-cost LiDARs through data-driven inference. We present DENALI, the first large-scale real-world dataset of space-time histograms from low-cost LiDARs capturing hidden objects. We capture time-resolved LiDAR histograms for 72,000 hidden-object scenes across diverse object shapes, positions, lighting conditions, and spatial resolutions. Using our dataset, we show that consumer LiDARs can enable accurate, data-driven NLOS perception. We further identify key scene and modeling factors that limit performance, as well as simulation-fidelity gaps that hinder current sim-to-real transfer, motivating future work toward scalable NLOS vision with consumer LiDARs.

  PublisherOA PDF

• Advances in Feed‐Forward 3D Reconstruction and View Synthesis: A Survey

  Computer Graphics Forum · 2026-05-06

  articleOpen access

  Abstract 3D reconstruction and view synthesis are foundational problems in computer vision, graphics, and immersive technologies such as augmented reality (AR), virtual reality (VR), and digital twins. Traditional methods rely on computationally intensive iterative optimization in a complex chain, limiting their applicability in real‐world scenarios. Recent advances in feed‐forward approaches, driven by deep learning, have revolutionized this field by enabling fast and generalizable 3D reconstruction and view synthesis. This survey offers a comprehensive review of feed‐forward techniques for 3D reconstruction and view synthesis, with a taxonomy according to the underlying representation architectures including point cloud, 3D Gaussian Splatting (3DGS), Neural Radiance Fields (NeRF), etc. We examine key tasks such as pose‐free reconstruction, dynamic 3D reconstruction, and 3D‐aware image and video synthesis, highlighting their applications in digital humans, SLAM, robotics, and beyond. In addition, we review commonly used datasets with detailed statistics, along with evaluation protocols for various downstream tasks. We conclude by discussing open research challenges and promising directions for future work, emphasizing the potential of feed‐forward approaches to advance the state of the art in 3D vision. The project page is available at https://fnzhan.com/projects/Feed‐Forward‐3D Feed‐Forward‐3D.

  PublisherOA PDFDOI

• DENALI: A Dataset Enabling Non-Line-of-Sight Spatial Reasoning with Low-Cost LiDARs

  arXiv (Cornell University) · 2026-04-17

  preprintOpen access

  Consumer LiDARs in mobile devices and robots typically output a single depth value per pixel. Yet internally, they record full time-resolved histograms containing direct and multi-bounce light returns; these multi-bounce returns encode rich non-line-of-sight (NLOS) cues that can enable perception of hidden objects in a scene. However, severe hardware limitations of consumer LiDARs make NLOS reconstruction with conventional methods difficult. In this work, we motivate a complementary direction: enabling NLOS perception with low-cost LiDARs through data-driven inference. We present DENALI, the first large-scale real-world dataset of space-time histograms from low-cost LiDARs capturing hidden objects. We capture time-resolved LiDAR histograms for 72,000 hidden-object scenes across diverse object shapes, positions, lighting conditions, and spatial resolutions. Using our dataset, we show that consumer LiDARs can enable accurate, data-driven NLOS perception. We further identify key scene and modeling factors that limit performance, as well as simulation-fidelity gaps that hinder current sim-to-real transfer, motivating future work toward scalable NLOS vision with consumer LiDARs.

  PublisherDOI

• Continuous First, Discrete Later: VQ-VAEs Without Dimensional Collapse

  arXiv (Cornell University) · 2026-05-07

  preprintOpen access

  While many approaches to improve VQ-VAE performance focus on codebook size and utilization, the effect of dimensional collapse, where trained VQ-VAE representations live in an extremely low-dimensional subspace (1-2% of full rank), remains unaddressed. We show theoretically and empirically that dimension collapse causes a hard loss lower bound that various codebook improvement techniques fail to surpass. Our analytic framework extends the sequential learning effect of Saxe et al. [2014] by introducing ideas from rate-distortion theory and explains how the latent collapse is caused by the VQ suppressing lower-variance directions. Our theory justifies a simple solution: a "warm-up phase" that trains the model as an (unquantized) autoencoder before introducing VQ. On both synthetic experiments and large-scale image (VQGAN) and audio (WavTokenizer) VQ-VAEs, we show that AE Warm-Up successfully restores representation dimension, leading to lower reconstruction and perceptual loss at the same training budget. Across codebook sizes $K \in$ {$2^{10}, 2^{14}, 2^{16}$}, AE warm-up raises VQGAN codebook effective dimension from 3-5 to 17-19 and reduces rFID by 17-35%; on WavTokenizer at $K \in$ {$2^{13}, 2^{14}$}, it raises codebook dimension from 4 to 17-19 and improves PESQ by 11-14%. We empirically characterize how warm-up duration governs the achievable final loss. In agreement with experiment, our theoretical analysis predicts downstream performance as a function of warm-up length, enabling an adaptive criterion for switching from AE Warm-up to VQ-VAE training.

  PublisherDOI

• From Competition to Collaborative Smelling: Navigating the Olfactory Gap in Human-AI Interaction

  2026-04-13

  articleOpen access

  Addressing the olfactory-verbal gap remains a key challenge in Human-Computer Interaction (HCI), as the subjective nature of smell often resists precise articulation. We introduce Smell with Genji, an Artificial Intelligence (AI)-mediated olfactory experience that adapts the traditional Japanese olfactory game Genji-kō into a research probe for structured comparison and articulation. Through an iterative development process, we describe a shift from a Competition Model, where AI benchmarks alignment with human judgments, to a Partnership Model, where AI functions as a co-smelling partner during iterative comparison. Leveraging Large Language Models (LLMs), the system transforms sensing latency into dialogic engagement within the interactional flow. Preliminary findings from two pilot studies (n = 16) suggest that the system facilitates novice users in organizing and articulating comparative scent judgments through data-informed interaction. Our work proposes that beyond technical precision, the value of olfactory AI can be found in its role as a collaborative partner within structured sensory comparison.

  PublisherDOI

• Continuous First, Discrete Later: VQ-VAEs Without Dimensional Collapse

  ArXiv.org · 2026-05-07

  articleOpen access

  While many approaches to improve VQ-VAE performance focus on codebook size and utilization, the effect of dimensional collapse, where trained VQ-VAE representations live in an extremely low-dimensional subspace (1-2% of full rank), remains unaddressed. We show theoretically and empirically that dimension collapse causes a hard loss lower bound that various codebook improvement techniques fail to surpass. Our analytic framework extends the sequential learning effect of Saxe et al. [2014] by introducing ideas from rate-distortion theory and explains how the latent collapse is caused by the VQ suppressing lower-variance directions. Our theory justifies a simple solution: a "warm-up phase" that trains the model as an (unquantized) autoencoder before introducing VQ. On both synthetic experiments and large-scale image (VQGAN) and audio (WavTokenizer) VQ-VAEs, we show that AE Warm-Up successfully restores representation dimension, leading to lower reconstruction and perceptual loss at the same training budget. Across codebook sizes $K \in$ {$2^{10}, 2^{14}, 2^{16}$}, AE warm-up raises VQGAN codebook effective dimension from 3-5 to 17-19 and reduces rFID by 17-35%; on WavTokenizer at $K \in$ {$2^{13}, 2^{14}$}, it raises codebook dimension from 4 to 17-19 and improves PESQ by 11-14%. We empirically characterize how warm-up duration governs the achievable final loss. In agreement with experiment, our theoretical analysis predicts downstream performance as a function of warm-up length, enabling an adaptive criterion for switching from AE Warm-up to VQ-VAE training.

  PublisherOA PDF

• Dialogues with AI Reduce Beliefs in Misinformation but Build No Lasting Discernment Skills

  2026-04-13

  articleOpen access

  Given the growing prevalence of fake information, including increasingly realistic AI-generated news, there is an urgent need to train people to better evaluate and detect misinformation. While interactions with AI have been shown to durably reduce people’s beliefs in false information, it is unclear whether these interactions also teach people the skills to discern false information themselves. We conducted a month-long study where 67 participants classified news headline-image pairs as real or fake, discussed their assessments with an AI system, followed by an unassisted evaluation of unseen news items to measure accuracy before, during, and after AI assistance. While AI assistance produced immediate improvements during AI-assisted sessions (+21% average), participants’ unassisted performance on new items declined significantly by 15.3% in week 4 compared to week 0. These results indicate that while AI may help immediately, it may ultimately degrade long-term misinformation detection abilities.

  PublisherDOI

• OpenFace 3.0: A Lightweight Multitask System for Comprehensive Facial Behavior Analysis

  ArXiv.org · 2025-06-03 · 2 citations

  preprintOpen access

  In recent years, there has been increasing interest in automatic facial behavior analysis systems from computing communities such as vision, multimodal interaction, robotics, and affective computing. Building upon the widespread utility of prior open-source facial analysis systems, we introduce OpenFace 3.0, an open-source toolkit capable of facial landmark detection, facial action unit detection, eye-gaze estimation, and facial emotion recognition. OpenFace 3.0 contributes a lightweight unified model for facial analysis, trained with a multi-task architecture across diverse populations, head poses, lighting conditions, video resolutions, and facial analysis tasks. By leveraging the benefits of parameter sharing through a unified model and training paradigm, OpenFace 3.0 exhibits improvements in prediction performance, inference speed, and memory efficiency over similar toolkits and rivals state-of-the-art models. OpenFace 3.0 can be installed and run with a single line of code and operate in real-time without specialized hardware. OpenFace 3.0 code for training models and running the system is freely available for research purposes and supports contributions from the community.

  PublisherOA PDFDOI

• ORION: Teaching Language Models to Reason Efficiently in the Language of Thought

  ArXiv.org · 2025-11-28

  preprintOpen access

  Large Reasoning Models (LRMs) achieve strong performance in mathematics, code generation, and task planning, but their reliance on long chains of verbose "thinking" tokens leads to high latency, redundancy, and incoherent reasoning paths. Inspired by the Language of Thought Hypothesis, which posits that human reasoning operates over a symbolic, compositional mental language called Mentalese, we introduce a framework that trains models to reason in a similarly compact style. Mentalese encodes abstract reasoning as ultra-compressed, structured tokens, enabling models to solve complex problems with far fewer steps. To improve both efficiency and accuracy, we propose SHORTER LENGTH PREFERENCE OPTIMIZATION (SLPO), a reinforcement learning method that rewards concise solutions that stay correct, while still allowing longer reasoning when needed. Applied to Mentalese-aligned models, SLPO yields significantly higher compression rates by enabling concise reasoning that preserves the benefits of detailed thinking without the computational overhead. Across benchmarks including AIME 2024 and 2025, MinervaMath, OlympiadBench, Math500, and AMC, our ORION models produce reasoning traces with 4-16x fewer tokens, achieve up to 5x lower inference latency, and reduce training costs by 7-9x relative to the DeepSeek R1 Distilled model, while maintaining 90-98% of its accuracy. ORION also surpasses Claude and ChatGPT-4o by up to 5% in accuracy while maintaining 2x compression. These results show that Mentalese-style compressed reasoning offers a step toward human-like cognitive efficiency, enabling real-time, cost-effective reasoning without sacrificing accuracy.

  PublisherOA PDFDOI

Frequent coauthors

• Louis‐Philippe Morency

  115 shared

• Ruslan Salakhutdinov

  59 shared

• Amir Zadeh

  Shenyang University of Technology

  32 shared

• Yiwei Lyu

  14 shared

• Ziyin Liu

  14 shared

• Yao-Hung Hubert Tsai

  12 shared

• Soujanya Poria

  9 shared

• Alex Wilf

  8 shared