Showing 1–26 of 26 results for author: Chi, P

Closing the Loop in Humanoid VLA: Persistent 3D Object Tokens for Verifiable Loco-Manipulation

Authors: Peng Ren, Haoyang Ge, Jiang Zhao, Cong Huang, Yukun Shi, Pei Chi, Kai Chen

Abstract: Vision-language-action policies are a promising foundation for general robot control, but long-horizon humanoid loco-manipulation requires the robot to treat task objects as persistent physical entities across movement, contact, occlusion, and recovery. We study this problem as object-state divergence: the object state used to condition a whole-body action can differ from the state used to decide… ▽ More Vision-language-action policies are a promising foundation for general robot control, but long-horizon humanoid loco-manipulation requires the robot to treat task objects as persistent physical entities across movement, contact, occlusion, and recovery. We study this problem as object-state divergence: the object state used to condition a whole-body action can differ from the state used to decide whether the action achieved the intended physical relation. We propose \emph{Persistent Object Tokenization} (POT), which maintains role-indexed 3D object records from RGB-D observations and converts them into object tokens for a whole-body action expert. Instantiated as \emph{POT-VLA}, the same object records condition action generation and support geometric predicate checks, yielding a closed-loop execution system in which object state is both actionable and verifiable. On a Unitree G1, POT-VLA improves a matched direct GR00T-N1.7 baseline from 39/80 to 71/80 successes over eight real-world task families. In an external Being-0-aligned reference, POT-VLA achieves 44/50 successes on aligned service tasks, compared with the 37/50 success reported by the Being-0 paper. The largest gains occur on tasks requiring maintained 3D relations, suggesting that persistent object-centered state is a useful abstraction for verifiable humanoid VLA execution. △ Less

Submitted 26 July, 2026; v1 submitted 20 July, 2026; originally announced July 2026.

A Semiparametric Framework for Stochastic Fundamental Diagram Modeling

Authors: Pengnan Chi, Xiaoliang Ma, Magnus Jansson, Magnus Nordenvaad

Abstract: The stochastic fundamental diagram (SFD) provides a probabilistic description of the relationship between traffic density and flow or speed, enabling uncertainty-aware traffic modeling. However, existing stochastic models frequently struggle to accommodate rigorous physical constraints while retaining sufficient flexibility to capture complex nonlinear patterns. To address this, we propose a novel… ▽ More The stochastic fundamental diagram (SFD) provides a probabilistic description of the relationship between traffic density and flow or speed, enabling uncertainty-aware traffic modeling. However, existing stochastic models frequently struggle to accommodate rigorous physical constraints while retaining sufficient flexibility to capture complex nonlinear patterns. To address this, we propose a novel semiparametric SFD modeling framework by leveraging specially designed functional forms. These functions intrinsically satisfy physical constraints defined on the moments of the conditional flow distribution given traffic density while incorporating neural-network-based structures to capture complex empirical patterns. We derive a system of moment-matching equations to convert physical constraints into the parameterization of the conditional distribution, proving that a unique solution exists for the location-scale family of distributions, thereby guaranteeing model well-posedness. Furthermore, we demonstrate that the framework can be extended to non-location-scale distributions, including those requiring additional boundary constraints. Empirical evaluations on a real-world dataset reveal that our approach consistently outperforms representative baselines, delivering superior probabilistic accuracy and robust uncertainty quantification, particularly in congested regimes. Overall, the proposed framework provides a theoretically grounded and flexible foundation for stochastic traffic flow modeling. △ Less

Submitted 17 July, 2026; originally announced July 2026.

Comments: 22 pages, 11 figures, 5 tables

TALAS: Teacher-Anchored Layer Alignment with Adaptive Sharpness-Aware Minimization for Embedding Distillation

Authors: Quoc Phong Dao, Hoang Son Nguyen, Pham Khanh Chi, Linh Ngo Van, Nguyen Thi Ngoc Diep, Thien Huu Nguyen, Trung Le

Abstract: Knowledge Distillation (KD) has established itself as a pivotal technique for compressing large pre-trained language models. However, existing methods that force a student to strictly mimic the teacher's sentence embeddings or internal features often incur prohibitive computational costs and yield suboptimal performance due to the inherent capacity gap. To address these challenges, we propose TALA… ▽ More Knowledge Distillation (KD) has established itself as a pivotal technique for compressing large pre-trained language models. However, existing methods that force a student to strictly mimic the teacher's sentence embeddings or internal features often incur prohibitive computational costs and yield suboptimal performance due to the inherent capacity gap. To address these challenges, we propose TALAS (Teacher-Anchored Layer Alignment with Sharpness-aware minimization), a unified framework that synergizes hierarchical (multi-layer) alignment with robust optimization. First, we introduce a Teacher-Anchored mechanism that selectively distills final sentence embeddings only into the student's upper layers, thereby reducing overhead while respecting capacity constraints. Second, we bridge the semantic gap in lower layers via Layer-Aligned Self-Distillation, which propagates knowledge top-down using internal geometric relational constraints in the embedding space. Finally, to prevent the student from memorizing point-wise teacher noise, we integrate Adaptive Sharpness-Aware Minimization (ASAM) into the training objective, guiding the model towards flat minima for enhanced generalization. Empirical results on standard sentence embedding benchmarks demonstrate that TALAS consistently outperforms strong distillation baselines while achieving superior training efficiency in terms of computational cost and memory footprint. △ Less

Submitted 19 June, 2026; originally announced June 2026.

Comments: ACL 2026

MTA: Multi-Granular Trajectory Alignment for Large Language Model Distillation

Authors: Pham Khanh Chi, Quoc Phong Dao, Thuat Nguyen, Linh Ngo Van, Trung Le, Thanh Hong Nguyen

Abstract: Knowledge distillation is a key technique for compressing large language models (LLMs), but most existing methods align representations at fixed layers or token-level outputs, ignoring how representations evolve across depth. As a result, the student is only weakly guided to capture the teacher's internal relational structure during distillation, which limits knowledge transfer. To address this li… ▽ More Knowledge distillation is a key technique for compressing large language models (LLMs), but most existing methods align representations at fixed layers or token-level outputs, ignoring how representations evolve across depth. As a result, the student is only weakly guided to capture the teacher's internal relational structure during distillation, which limits knowledge transfer. To address this limitation, we propose Multi-Granular Trajectory Alignment (MTA), a framework that aligns teacher and student representations along their layer-wise transformation trajectory. MTA adopts a layer-adaptive strategy: lower layers are aligned at the word level to preserve lexical information, while higher layers operate on phrase-level spans (e.g., noun and verb phrases) to capture compositional semantics. We instantiate this idea through a Dynamic Structural Alignment loss that matches the relative geometry among semantic units within each layer. This design is motivated by empirical findings that Transformer representations become increasingly abstract with depth, and is also consistent with linguistic views in which higher-level meaning emerges through the composition of lower-level lexical units. We further incorporate a Hidden Representation Alignment loss to directly align selected teacher-student layers. Experiments show that MTA consistently outperforms state-of-the-art baselines on standard benchmarks, with ablations confirming the contribution of each component. △ Less

Submitted 2 June, 2026; v1 submitted 2 May, 2026; originally announced May 2026.

Comments: ACL 2026

SRA: Span Representation Alignment for Large Language Model Distillation

Authors: Quoc Phong Dao, Hoang Son Nguyen, Pham Khanh Chi, Tung Nguyen, Linh Ngo Van, Nguyen Thi Ngoc Diep, Trung Le

Abstract: Cross-Tokenizer Knowledge Distillation (CTKD) enables knowledge transfer between a large language model and a smaller student, even when they employ different tokenizers. While existing approaches mainly focus on token-level alignment strategies, which are often brittle and sensitive to discrepancies between tokenizers, we argue that the method of aggregating tokens into more robust representation… ▽ More Cross-Tokenizer Knowledge Distillation (CTKD) enables knowledge transfer between a large language model and a smaller student, even when they employ different tokenizers. While existing approaches mainly focus on token-level alignment strategies, which are often brittle and sensitive to discrepancies between tokenizers, we argue that the method of aggregating tokens into more robust representations before distillation is of equal importance. In this paper, we introduce \textbf{SRA} (\textbf{S}pan \textbf{R}epresentation \textbf{A}lignment for Large Language Model Distillation), a novel framework that reframes CTKD through the physical lens of Multi-Particle Dynamical Systems. SRA shifts the fundamental unit of alignment from tokens to robust, tokenizer-agnostic spans. We model each span as a cluster of particles and represent its state by its Center of Mass (CoM) - an attention-weighted average that captures rich semantic information. We leverage the concept of span centers of mass with attention-derived weighting to prioritize the most salient spans. In addition, we employ a geometric regularizer to preserve the structural integrity of the representation space and introduce aligned span logit distillation to enhance knowledge transfer across models. In challenging cross-architecture distillation experiments, SRA consistently and significantly outperforms state-of-the-art CTKD baselines, validating our physically-grounded approach. △ Less

Submitted 2 June, 2026; v1 submitted 1 May, 2026; originally announced May 2026.

Comments: ACL 2026

Facial-Expression-Aware Prompting for Empathetic LLM Tutoring

Authors: Shuangquan Feng, Laura Fleig, Ruisen Tu, Philip Chi, Edmund Bu, Melinda Ozel, Junhua Ma, Teng Fei, Virginia R. de Sa

Abstract: Large language models (LLMs) enable increasingly capable tutoring-style conversational agents, yet effective tutoring requires sensitivity to learners' affective and cognitive states beyond text alone. Facial expressions provide immediate and practical cues of confusion, frustration, or engagement, but remain underexplored in LLM-driven tutoring. We investigate whether facial-expression-aware sign… ▽ More Large language models (LLMs) enable increasingly capable tutoring-style conversational agents, yet effective tutoring requires sensitivity to learners' affective and cognitive states beyond text alone. Facial expressions provide immediate and practical cues of confusion, frustration, or engagement, but remain underexplored in LLM-driven tutoring. We investigate whether facial-expression-aware signals can improve empathetic tutoring responses through prompt-level integration, without end-to-end retraining. We build a scalable simulated tutoring environment where a student agent exhibits diverse facial behaviors from a large unlabeled human facial expression video dataset, and compare four tutor variants: a text-only LLM baseline, a multimodal baseline using a random facial frame, and two Action Unit estimation model (AUM)-based methods that either inject textual AU descriptions or select a peak-expression frame for visual grounding. Across 960 multi-turn conversations spanning three tutor backbones (GPT-5.1, Claude Opus 4.5, and Gemini 2.5 Pro), we evaluate targeted pairwise comparisons with five human raters and an exhaustive AI evaluator. AU-based conditioning consistently improves empathetic responsiveness to facial expressions across all tutor backbones, while AUM-guided peak-frame selection outperforms random-frame visual input. Textual AU abstraction and peak-frame visual injection show model-dependent advantages. Control analyses show that this improvement does not come at the expense of worse pedagogical clarity or responsiveness to textual cues. Overall, our results show that lightweight, structured facial expression representations can meaningfully enhance empathy in LLM-based tutoring systems with minimal overhead. Future work should evaluate these methods using real student facial data collected during authentic learning interactions. △ Less

Submitted 28 July, 2026; v1 submitted 10 March, 2026; originally announced April 2026.

CyboRacket: A Perception-to-Action Framework for Humanoid Racket Sports

Authors: Peng Ren, Chuan Qi, Haoyang Ge, Qiyuan Su, Xuguo He, Cong Huang, Pei Chi, Jiang Zhao, Kai Chen

Abstract: Dynamic ball-interaction tasks remain challenging for robots because they require tight perception-action coupling under limited reaction time. This challenge is especially pronounced in humanoid racket sports, where successful interception depends on accurate visual tracking, trajectory prediction, coordinated stepping, and stable whole-body striking. Existing robotic racket-sport systems often r… ▽ More Dynamic ball-interaction tasks remain challenging for robots because they require tight perception-action coupling under limited reaction time. This challenge is especially pronounced in humanoid racket sports, where successful interception depends on accurate visual tracking, trajectory prediction, coordinated stepping, and stable whole-body striking. Existing robotic racket-sport systems often rely on external motion capture for state estimation or on task-specific low-level controllers that must be retrained across tasks and platforms. We present CyboRacket, a hierarchical perception-to-action framework for humanoid racket sports that integrates onboard visual perception, physics-based trajectory prediction, and large-scale pre-trained whole-body control. The framework uses onboard cameras to track the incoming object, predicts its future trajectory, and converts the estimated interception state into target end-effector and base-motion commands for whole-body execution by SONIC on the Unitree G1 humanoid robot. We evaluate the proposed framework in a vision-based humanoid tennis-hitting task. Experimental results demonstrate real-time visual tracking, trajectory prediction, and successful striking using purely onboard sensing. △ Less

Submitted 15 March, 2026; originally announced March 2026.

Cybo-Waiter: A Physical Agentic Framework for Humanoid Whole-Body Locomotion-Manipulation

Authors: Peng Ren, Haoyang Ge, Chuan Qi, Cong Huang, Hong Li, Jiang Zhao, Pei Chi, Kai Chen

Abstract: Robots are increasingly expected to execute open ended natural language requests in human environments, which demands reliable long horizon execution under partial observability. This is especially challenging for humanoids because locomotion and manipulation are tightly coupled through stance, reachability, and balance. We present a humanoid agent framework that turns VLM plans into verifiable ta… ▽ More Robots are increasingly expected to execute open ended natural language requests in human environments, which demands reliable long horizon execution under partial observability. This is especially challenging for humanoids because locomotion and manipulation are tightly coupled through stance, reachability, and balance. We present a humanoid agent framework that turns VLM plans into verifiable task programs and closes the loop with multi object 3D geometric supervision. A VLM planner compiles each instruction into a typed JSON sequence of subtasks with explicit predicate based preconditions and success conditions. Using SAM3 and RGB-D, we ground all task relevant entities in 3D, estimate object centroids and extents, and evaluate predicates over stable frames to obtain condition level diagnostics. The supervisor uses these diagnostics to verify subtask completion and to provide condition-level feedback for progression and replanning. We execute each subtask by coordinating humanoid locomotion and whole-body manipulation, selecting feasible motion primitives under reachability and balance constraints. Experiments on tabletop manipulation and long horizon humanoid loco manipulation tasks show improved robustness from multi object grounding, temporal stability, and recovery driven replanning. △ Less

Submitted 11 March, 2026; originally announced March 2026.

PanoDP: Learning Collision-Free Navigation with Panoramic Depth and Differentiable Physics

Authors: Hao Zhong, Pei Chi, Jiang Zhao, Shenghai Yuan, Xuyang Gao, Thien-Minh Nguyen, Lihua Xie

Abstract: Autonomous collision-free navigation in cluttered environments requires safe decision-making under partial observability with both static structure and dynamic obstacles. We present \textbf{PanoDP}, a communication-free learning framework that combines four-view panoramic depth perception with differentiable-physics-based training signals. PanoDP encodes panoramic depth using a lightweight CNN and… ▽ More Autonomous collision-free navigation in cluttered environments requires safe decision-making under partial observability with both static structure and dynamic obstacles. We present \textbf{PanoDP}, a communication-free learning framework that combines four-view panoramic depth perception with differentiable-physics-based training signals. PanoDP encodes panoramic depth using a lightweight CNN and optimizes policies with dense differentiable collision and motion-feasibility terms, improving training stability beyond sparse terminal collisions. We evaluate PanoDP on a controlled ring-to-center benchmark with systematic sweeps over agent count, obstacle density/layout, and dynamic behaviors, and further test out-of-distribution generalization in an external simulator (e.g., AirSim). Across settings, PanoDP increases collision-free and completion rates over single-view and non-physics-guided baselines under matched training budgets, and ablations (view masking, rotation augmentation) confirm the policy leverages 360-degree information. Code will be open source upon acceptance. △ Less

Submitted 8 March, 2026; originally announced March 2026.

DWA-KD: Dual-Space Weighting and Time-Warped Alignment for Cross-Tokenizer Knowledge Distillation

Authors: Duc Trung Vu, Pham Khanh Chi, Dat Phi Van, Linh Ngo Van, Sang Dinh, Trung Le

Abstract: Knowledge Distillation (KD) has emerged as a crucial technique for compressing Large Language Models (LLMs). Although existing cross-tokenizer KD methods have made notable progress, their effectiveness remains constrained by suboptimal alignment across sequence and vocabulary levels. To address these limitations, we introduce Dual-Space Weighting and Time-Warped Alignment (DWA-KD), a novel cross-t… ▽ More Knowledge Distillation (KD) has emerged as a crucial technique for compressing Large Language Models (LLMs). Although existing cross-tokenizer KD methods have made notable progress, their effectiveness remains constrained by suboptimal alignment across sequence and vocabulary levels. To address these limitations, we introduce Dual-Space Weighting and Time-Warped Alignment (DWA-KD), a novel cross-tokenizer distillation framework that enhances token-wise distillation through dual-space entropy-based weighting and achieves precise sequence-level alignment by leveraging both lexical and semantic information. At the token level, DWA-KD maps teacher representations into the student space and vice versa, performing dual-space KD via Kullback-Leibler divergence (KL). The process is modulated by dual-space weights that up-weight tokens where the student is uncertain and the teacher is confident, thereby focusing learning on informative tokens rather than treating all positions equally. At the sequence level, DWA-KD applies Soft Dynamic Time Warping (Soft-DTW) to both the embedding and final hidden-state layers, enabling robust alignment of lexical and contextual semantics between teacher and student sequences. Extensive experiments across diverse NLP benchmarks demonstrate that DWA-KD outperforms state-of-the-art KD baselines, while ablation studies confirm the complementary contributions of entropy-based token weighting and embedding and final hidden state layer Soft-DTW alignment. △ Less

Submitted 25 February, 2026; originally announced February 2026.

Comments: EACL Findings

BigBang-Proton Technical Report: Next-Word-Prediction is Scientific Multitask Learner

Authors: Hengkui Wu, Liujiang Liu, Jihua He, Qihao Wang, Keke Zhao, Shuyang Hu, Renle Fu, Dahao Liang, Lingyu Zeng, Bruce Liu, Yuan Liu, Jin Zhan, Jiaqiang Niu, Xinglong Jia, Yaqin Hu, Wenjun Ji, Panpan Chi, Ken Chen, Hengyuan Wu, Yingsi Xin, Yongfeng Zhu, Yuexin Wang, Manqi Ruan, Ningtao Bian, Xiaohua Wu , et al. (1 additional authors not shown)

Abstract: We introduce BigBang-Proton, a unified sequence-based architecture for auto-regressive language modeling pretrained on cross-scale, cross-structure, cross-discipline real-world scientific tasks to construct a scientific multi-task learner. BigBang-Proton incorporates three fundamental innovations compared to mainstream general-purpose LLMs: Theory-Experiment Learning paradigm aligns large-scale nu… ▽ More We introduce BigBang-Proton, a unified sequence-based architecture for auto-regressive language modeling pretrained on cross-scale, cross-structure, cross-discipline real-world scientific tasks to construct a scientific multi-task learner. BigBang-Proton incorporates three fundamental innovations compared to mainstream general-purpose LLMs: Theory-Experiment Learning paradigm aligns large-scale numerical experimental data with theoretical text corpora; Binary Patch Encoding replaces byte pair encoding(BPE) tokenization; Monte Carlo Attention substitutes traditional transformer architectures. Through next-word-prediction pretraining on cross-discipline scientific datasets of real-world problems mixed with general textual corpus, followed by fine-tuning and inference on downstream tasks, BigBang-Proton demonstrates 100\% accuracy in up to 50-digit arithmetic addition operations, performance on par with leading specialized models in particle physics jet tagging, matching MAE of specialized models in inter-atomic potential simulation, performance comparable to traditional spatiotemporal models in water quality prediction, and benchmark-exceeding performance in genome modeling. These results prove that language-guided scientific computing can match or exceed the performance of task-specific scientific models while maintaining multitask learning capabilities. We further hypothesize to scale the pretraining to the universe scale as a fundamental step toward developing material world foundational model. △ Less

Submitted 30 September, 2025; originally announced October 2025.

Comments: 93 pages, 39 figures

MSC Class: 68T05; 68T50; 00A69; 94A99 ACM Class: I.2.6; I.2.7; J.2; I.6.3; K.4.1

Scaling Particle Collision Data Analysis

Authors: Hengkui Wu, Panpan Chi, Yongfeng Zhu, Liujiang Liu, Shuyang Hu, Yuexin Wang, Chen Zhou, Qihao Wang, Yingsi Xin, Bruce Liu, Dahao Liang, Xinglong Jia, Manqi Ruan

Abstract: For decades, researchers have developed task-specific models to address scientific challenges across diverse disciplines. Recently, large language models (LLMs) have shown enormous capabilities in handling general tasks; however, these models encounter difficulties in addressing real-world scientific problems, particularly in domains involving large-scale numerical data analysis, such as experimen… ▽ More For decades, researchers have developed task-specific models to address scientific challenges across diverse disciplines. Recently, large language models (LLMs) have shown enormous capabilities in handling general tasks; however, these models encounter difficulties in addressing real-world scientific problems, particularly in domains involving large-scale numerical data analysis, such as experimental high energy physics. This limitation is primarily due to BPE tokenization's inefficacy with numerical data. In this paper, we propose a task-agnostic architecture, BBT-Neutron, which employs a binary tokenization method to facilitate pretraining on a mixture of textual and large-scale numerical experimental data. We demonstrate the application of BBT-Neutron to Jet Origin Identification (JoI), a critical categorization challenge in high-energy physics that distinguishes jets originating from various quarks or gluons. Our results indicate that BBT-Neutron achieves comparable performance to state-of-the-art task-specific JoI models. Furthermore, we examine the scaling behavior of BBT-Neutron's performance with increasing data volume, suggesting the potential for BBT-Neutron to serve as a foundational model for particle physics data analysis, with possible extensions to a broad spectrum of scientific computing applications for Big Science experiments, industrial manufacturing and spacial computing. The project code is available at https://github.com/supersymmetry-technologies/bbt-neutron. △ Less

Submitted 9 December, 2024; v1 submitted 28 November, 2024; originally announced December 2024.

A Large-Scale Evaluation of Speech Foundation Models

Authors: Shu-wen Yang, Heng-Jui Chang, Zili Huang, Andy T. Liu, Cheng-I Lai, Haibin Wu, Jiatong Shi, Xuankai Chang, Hsiang-Sheng Tsai, Wen-Chin Huang, Tzu-hsun Feng, Po-Han Chi, Yist Y. Lin, Yung-Sung Chuang, Tzu-Hsien Huang, Wei-Cheng Tseng, Kushal Lakhotia, Shang-Wen Li, Abdelrahman Mohamed, Shinji Watanabe, Hung-yi Lee

Abstract: The foundation model paradigm leverages a shared foundation model to achieve state-of-the-art (SOTA) performance for various tasks, requiring minimal downstream-specific modeling and data annotation. This approach has proven crucial in the field of Natural Language Processing (NLP). However, the speech processing community lacks a similar setup to explore the paradigm systematically. In this work,… ▽ More The foundation model paradigm leverages a shared foundation model to achieve state-of-the-art (SOTA) performance for various tasks, requiring minimal downstream-specific modeling and data annotation. This approach has proven crucial in the field of Natural Language Processing (NLP). However, the speech processing community lacks a similar setup to explore the paradigm systematically. In this work, we establish the Speech processing Universal PERformance Benchmark (SUPERB) to study the effectiveness of the paradigm for speech. We propose a unified multi-tasking framework to address speech processing tasks in SUPERB using a frozen foundation model followed by task-specialized, lightweight prediction heads. Combining our results with community submissions, we verify that the foundation model paradigm is promising for speech, and our multi-tasking framework is simple yet effective, as the best-performing foundation model shows competitive generalizability across most SUPERB tasks. For reproducibility and extensibility, we have developed a long-term maintained platform that enables deterministic benchmarking, allows for result sharing via an online leaderboard, and promotes collaboration through a community-driven benchmark database to support new development cycles. Finally, we conduct a series of analyses to offer an in-depth understanding of SUPERB and speech foundation models, including information flows across tasks inside the models, the correctness of the weighted-sum benchmarking protocol and the statistical significance and robustness of the benchmark. △ Less

Submitted 29 May, 2024; v1 submitted 14 April, 2024; originally announced April 2024.

Comments: The extended journal version for SUPERB and SUPERB-SG. Published in IEEE/ACM TASLP. The Arxiv version is preferred

Automatic Multi-Path Web Story Creation from a Structural Article

Authors: Daniel Nkemelu, Peggy Chi, Daniel Castro Chin, Krishna Srinivasan, Irfan Essa

Abstract: Web articles such as Wikipedia serve as one of the major sources of knowledge dissemination and online learning. However, their in-depth information--often in a dense text format--may not be suitable for mobile browsing, even in a responsive UI. We propose an automatic approach that converts a structural article of any length into a set of interactive Web Stories that are ideal for mobile experien… ▽ More Web articles such as Wikipedia serve as one of the major sources of knowledge dissemination and online learning. However, their in-depth information--often in a dense text format--may not be suitable for mobile browsing, even in a responsive UI. We propose an automatic approach that converts a structural article of any length into a set of interactive Web Stories that are ideal for mobile experiences. We focused on Wikipedia articles and developed Wiki2Story, a pipeline based on language and layout models, to demonstrate the concept. Wiki2Story dynamically slices an article and plans one to multiple Story paths according to the document hierarchy. For each slice, it generates a multi-page summary Story composed of text and image pairs in visually-appealing layouts. We derived design principles from an analysis of manually-created Story practices. We executed our pipeline on 500 Wikipedia documents and conducted user studies to review selected outputs. Results showed that Wiki2Story effectively captured and presented salient content from the original articles and sparked interest in viewers. △ Less

Submitted 3 October, 2023; originally announced October 2023.

ConceptEVA: Concept-Based Interactive Exploration and Customization of Document Summaries

Authors: Xiaoyu Zhang, Jianping Li, Po-Wei Chi, Senthil Chandrasegaran, Kwan-Liu Ma

Abstract: With the most advanced natural language processing and artificial intelligence approaches, effective summarization of long and multi-topic documents -- such as academic papers -- for readers from different domains still remains a challenge. To address this, we introduce ConceptEVA, a mixed-initiative approach to generate, evaluate, and customize summaries for long and multi-topic documents. Concep… ▽ More With the most advanced natural language processing and artificial intelligence approaches, effective summarization of long and multi-topic documents -- such as academic papers -- for readers from different domains still remains a challenge. To address this, we introduce ConceptEVA, a mixed-initiative approach to generate, evaluate, and customize summaries for long and multi-topic documents. ConceptEVA incorporates a custom multi-task longformer encoder decoder to summarize longer documents. Interactive visualizations of document concepts as a network reflecting both semantic relatedness and co-occurrence help users focus on concepts of interest. The user can select these concepts and automatically update the summary to emphasize them. We present two iterations of ConceptEVA evaluated through an expert review and a within-subjects study. We find that participants' satisfaction with customized summaries through ConceptEVA is higher than their own manually-generated summary, while incorporating critique into the summaries proved challenging. Based on our findings, we make recommendations for designing summarization systems incorporating mixed-initiative interactions. △ Less

Submitted 31 March, 2023; originally announced March 2023.

Comments: 16 pages, 7 figures

Learning to Generate Prompts for Dialogue Generation through Reinforcement Learning

Authors: Hsuan Su, Pohan Chi, Shih-Cheng Huang, Chung Ho Lam, Saurav Sahay, Shang-Tse Chen, Hung-yi Lee

Abstract: Much literature has shown that prompt-based learning is an efficient method to make use of the large pre-trained language model. Recent works also exhibit the possibility of steering a chatbot's output by plugging in an appropriate prompt. Gradient-based methods are often used to perturb the prompts. However, some language models are not even available to the public. In this work, we first explore… ▽ More Much literature has shown that prompt-based learning is an efficient method to make use of the large pre-trained language model. Recent works also exhibit the possibility of steering a chatbot's output by plugging in an appropriate prompt. Gradient-based methods are often used to perturb the prompts. However, some language models are not even available to the public. In this work, we first explored the combination of prompting and reinforcement learning (RL) to steer models' generation without accessing any of the models' parameters. Second, to reduce the training effort and enhance the generalizability to the unseen task, we apply multi-task learning to make the model learn to generalize to new tasks better. The experiment results show that our proposed method can successfully control several state-of-the-art (SOTA) dialogue models without accessing their parameters. Furthermore, the model demonstrates the strong ability to quickly adapt to an unseen task in fewer steps than the baseline model. △ Less

Submitted 13 October, 2022; v1 submitted 8 June, 2022; originally announced June 2022.

Leveraging Sequence Embedding and Convolutional Neural Network for Protein Function Prediction

Authors: Wei-Cheng Tseng, Po-Han Chi, Jia-Hua Wu, Min Sun

Abstract: The capability of accurate prediction of protein functions and properties is essential in the biotechnology industry, e.g. drug development and artificial protein synthesis, etc. The main challenges of protein function prediction are the large label space and the lack of labeled training data. Our method leverages unsupervised sequence embedding and the success of deep convolutional neural network… ▽ More The capability of accurate prediction of protein functions and properties is essential in the biotechnology industry, e.g. drug development and artificial protein synthesis, etc. The main challenges of protein function prediction are the large label space and the lack of labeled training data. Our method leverages unsupervised sequence embedding and the success of deep convolutional neural network to overcome these challenges. In contrast, most of the existing methods delete the rare protein functions to reduce the label space. Furthermore, some existing methods require additional bio-information (e.g., the 3-dimensional structure of the proteins) which is difficult to be determined in biochemical experiments. Our proposed method significantly outperforms the other methods on the publicly available benchmark using only protein sequences as input. This allows the process of identifying protein functions to be sped up. △ Less

Submitted 1 December, 2021; originally announced December 2021.

Comments: Published in NeurIPS 2018 Machine Learning for Molecules and Materials Workshop

HelpViz: Automatic Generation of Contextual Visual MobileTutorials from Text-Based Instructions

Authors: Mingyuan Zhong, Gang Li, Peggy Chi, Yang Li

Abstract: We present HelpViz, a tool for generating contextual visual mobile tutorials from text-based instructions that are abundant on the web. HelpViz transforms text instructions to graphical tutorials in batch, by extracting a sequence of actions from each text instruction through an instruction parsing model, and executing the extracted actions on a simulation infrastructure that manages an array of A… ▽ More We present HelpViz, a tool for generating contextual visual mobile tutorials from text-based instructions that are abundant on the web. HelpViz transforms text instructions to graphical tutorials in batch, by extracting a sequence of actions from each text instruction through an instruction parsing model, and executing the extracted actions on a simulation infrastructure that manages an array of Android emulators. The automatic execution of each instruction produces a set of graphical and structural assets, including images, videos, and metadata such as clicked elements for each step. HelpViz then synthesizes a tutorial by combining parsed text instructions with the generated assets, and contextualizes the tutorial to user interaction by tracking the user's progress and highlighting the next step. Our experiments with HelpViz indicate that our pipeline improved tutorial execution robustness and that participants preferred tutorials generated by HelpViz over text-based instructions. HelpViz promises a cost-effective approach for generating contextual visual tutorials for mobile interaction at scale. △ Less

Submitted 6 August, 2021; originally announced August 2021.

Comments: Accepted to UIST'21

Automatic Non-Linear Video Editing Transfer

Authors: Nathan Frey, Peggy Chi, Weilong Yang, Irfan Essa

Abstract: We propose an automatic approach that extracts editing styles in a source video and applies the edits to matched footage for video creation. Our Computer Vision based techniques considers framing, content type, playback speed, and lighting of each input video segment. By applying a combination of these features, we demonstrate an effective method that automatically transfers the visual and tempora… ▽ More We propose an automatic approach that extracts editing styles in a source video and applies the edits to matched footage for video creation. Our Computer Vision based techniques considers framing, content type, playback speed, and lighting of each input video segment. By applying a combination of these features, we demonstrate an effective method that automatically transfers the visual and temporal styles from professionally edited videos to unseen raw footage. We evaluated our approach with real-world videos that contained a total of 3872 video shots of a variety of editing styles, including different subjects, camera motions, and lighting. We reported feedback from survey participants who reviewed a set of our results. △ Less

Submitted 14 May, 2021; originally announced May 2021.

Comments: Published to AI for Content Creation Workshop at CVPR 2021

Journal ref: AI for Content Creation Workshop at CVPR 2021

SpeechNet: A Universal Modularized Model for Speech Processing Tasks

Authors: Yi-Chen Chen, Po-Han Chi, Shu-wen Yang, Kai-Wei Chang, Jheng-hao Lin, Sung-Feng Huang, Da-Rong Liu, Chi-Liang Liu, Cheng-Kuang Lee, Hung-yi Lee

Abstract: There is a wide variety of speech processing tasks ranging from extracting content information from speech signals to generating speech signals. For different tasks, model networks are usually designed and tuned separately. If a universal model can perform multiple speech processing tasks, some tasks might be improved with the related abilities learned from other tasks. The multi-task learning of… ▽ More There is a wide variety of speech processing tasks ranging from extracting content information from speech signals to generating speech signals. For different tasks, model networks are usually designed and tuned separately. If a universal model can perform multiple speech processing tasks, some tasks might be improved with the related abilities learned from other tasks. The multi-task learning of a wide variety of speech processing tasks with a universal model has not been studied. This paper proposes a universal modularized model, SpeechNet, which treats all speech processing tasks into a speech/text input and speech/text output format. We select five essential speech processing tasks for multi-task learning experiments with SpeechNet. We show that SpeechNet learns all of the above tasks, and we further analyze which tasks can be improved by other tasks. SpeechNet is modularized and flexible for incorporating more modules, tasks, or training approaches in the future. We release the code and experimental settings to facilitate the research of modularized universal models and multi-task learning of speech processing tasks. △ Less

Submitted 31 May, 2021; v1 submitted 7 May, 2021; originally announced May 2021.

SUPERB: Speech processing Universal PERformance Benchmark

Authors: Shu-wen Yang, Po-Han Chi, Yung-Sung Chuang, Cheng-I Jeff Lai, Kushal Lakhotia, Yist Y. Lin, Andy T. Liu, Jiatong Shi, Xuankai Chang, Guan-Ting Lin, Tzu-Hsien Huang, Wei-Cheng Tseng, Ko-tik Lee, Da-Rong Liu, Zili Huang, Shuyan Dong, Shang-Wen Li, Shinji Watanabe, Abdelrahman Mohamed, Hung-yi Lee

Abstract: Self-supervised learning (SSL) has proven vital for advancing research in natural language processing (NLP) and computer vision (CV). The paradigm pretrains a shared model on large volumes of unlabeled data and achieves state-of-the-art (SOTA) for various tasks with minimal adaptation. However, the speech processing community lacks a similar setup to systematically explore the paradigm. To bridge… ▽ More Self-supervised learning (SSL) has proven vital for advancing research in natural language processing (NLP) and computer vision (CV). The paradigm pretrains a shared model on large volumes of unlabeled data and achieves state-of-the-art (SOTA) for various tasks with minimal adaptation. However, the speech processing community lacks a similar setup to systematically explore the paradigm. To bridge this gap, we introduce Speech processing Universal PERformance Benchmark (SUPERB). SUPERB is a leaderboard to benchmark the performance of a shared model across a wide range of speech processing tasks with minimal architecture changes and labeled data. Among multiple usages of the shared model, we especially focus on extracting the representation learned from SSL due to its preferable re-usability. We present a simple framework to solve SUPERB tasks by learning task-specialized lightweight prediction heads on top of the frozen shared model. Our results demonstrate that the framework is promising as SSL representations show competitive generalizability and accessibility across SUPERB tasks. We release SUPERB as a challenge with a leaderboard and a benchmark toolkit to fuel the research in representation learning and general speech processing. △ Less

Submitted 15 October, 2021; v1 submitted 3 May, 2021; originally announced May 2021.

Comments: To appear in Interspeech 2021

Input-independent Attention Weights Are Expressive Enough: A Study of Attention in Self-supervised Audio Transformers

Authors: Tsung-Han Wu, Chun-Chen Hsieh, Yen-Hao Chen, Po-Han Chi, Hung-yi Lee

Abstract: In this paper, we seek solutions for reducing the computation complexity of transformer-based models for speech representation learning. We evaluate 10 attention algorithms; then, we pre-train the transformer-based model with those attention algorithms in a self-supervised fashion and treat them as feature extractors on downstream tasks, including phoneme classification and speaker classification.… ▽ More In this paper, we seek solutions for reducing the computation complexity of transformer-based models for speech representation learning. We evaluate 10 attention algorithms; then, we pre-train the transformer-based model with those attention algorithms in a self-supervised fashion and treat them as feature extractors on downstream tasks, including phoneme classification and speaker classification. With the assistance of t-SNE, PCA and some observation, the attention weights in self-supervised audio transformers can be categorized into four general cases. Based on these cases and some analyses, we are able to use a specific set of attention weights to initialize the model. Our approach shows comparable performance to the typical self-attention yet requires 20% less time in both training and inference. △ Less

Submitted 3 November, 2020; v1 submitted 9 June, 2020; originally announced June 2020.

Audio ALBERT: A Lite BERT for Self-supervised Learning of Audio Representation

Authors: Po-Han Chi, Pei-Hung Chung, Tsung-Han Wu, Chun-Cheng Hsieh, Yen-Hao Chen, Shang-Wen Li, Hung-yi Lee

Abstract: For self-supervised speech processing, it is crucial to use pretrained models as speech representation extractors. In recent works, increasing the size of the model has been utilized in acoustic model training in order to achieve better performance. In this paper, we propose Audio ALBERT, a lite version of the self-supervised speech representation model. We use the representations with two downstr… ▽ More For self-supervised speech processing, it is crucial to use pretrained models as speech representation extractors. In recent works, increasing the size of the model has been utilized in acoustic model training in order to achieve better performance. In this paper, we propose Audio ALBERT, a lite version of the self-supervised speech representation model. We use the representations with two downstream tasks, speaker identification, and phoneme classification. We show that Audio ALBERT is capable of achieving competitive performance with those huge models in the downstream tasks while utilizing 91\% fewer parameters. Moreover, we use some simple probing models to measure how much the information of the speaker and phoneme is encoded in latent representations. In probing experiments, we find that the latent representations encode richer information of both phoneme and speaker than that of the last layer. △ Less

Submitted 3 May, 2021; v1 submitted 18 May, 2020; originally announced May 2020.

Comments: Accepted by IEEE Spoken Language Technology Workshop 2021

BERT's output layer recognizes all hidden layers? Some Intriguing Phenomena and a simple way to boost BERT

Authors: Wei-Tsung Kao, Tsung-Han Wu, Po-Han Chi, Chun-Cheng Hsieh, Hung-Yi Lee

Abstract: Although Bidirectional Encoder Representations from Transformers (BERT) have achieved tremendous success in many natural language processing (NLP) tasks, it remains a black box. A variety of previous works have tried to lift the veil of BERT and understand each layer's functionality. In this paper, we found that surprisingly the output layer of BERT can reconstruct the input sentence by directly t… ▽ More Although Bidirectional Encoder Representations from Transformers (BERT) have achieved tremendous success in many natural language processing (NLP) tasks, it remains a black box. A variety of previous works have tried to lift the veil of BERT and understand each layer's functionality. In this paper, we found that surprisingly the output layer of BERT can reconstruct the input sentence by directly taking each layer of BERT as input, even though the output layer has never seen the input other than the final hidden layer. This fact remains true across a wide variety of BERT-based models, even when some layers are duplicated. Based on this observation, we propose a quite simple method to boost the performance of BERT. By duplicating some layers in the BERT-based models to make it deeper (no extra training required in this step), they obtain better performance in the downstream tasks after fine-tuning. △ Less

Submitted 15 February, 2021; v1 submitted 25 January, 2020; originally announced January 2020.

Comments: 7 pages, 8 figures, 3 tables

Mockingjay: Unsupervised Speech Representation Learning with Deep Bidirectional Transformer Encoders

Authors: Andy T. Liu, Shu-wen Yang, Po-Han Chi, Po-chun Hsu, Hung-yi Lee

Abstract: We present Mockingjay as a new speech representation learning approach, where bidirectional Transformer encoders are pre-trained on a large amount of unlabeled speech. Previous speech representation methods learn through conditioning on past frames and predicting information about future frames. Whereas Mockingjay is designed to predict the current frame through jointly conditioning on both past a… ▽ More We present Mockingjay as a new speech representation learning approach, where bidirectional Transformer encoders are pre-trained on a large amount of unlabeled speech. Previous speech representation methods learn through conditioning on past frames and predicting information about future frames. Whereas Mockingjay is designed to predict the current frame through jointly conditioning on both past and future contexts. The Mockingjay representation improves performance for a wide range of downstream tasks, including phoneme classification, speaker recognition, and sentiment classification on spoken content, while outperforming other approaches. Mockingjay is empirically powerful and can be fine-tuned with downstream models, with only 2 epochs we further improve performance dramatically. In a low resource setting with only 0.1% of labeled data, we outperform the result of Mel-features that uses all 100% labeled data. △ Less

Submitted 2 February, 2020; v1 submitted 24 October, 2019; originally announced October 2019.

Comments: Accepted by ICASSP 2020, Lecture Session

Journal ref: ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

Predicting The Performance of Minimax and Product in Game-Tree

Authors: Ping-Chung Chi, Dana Nau

Abstract: The discovery that the minimax decision rule performs poorly in some games has sparked interest in possible alternatives to minimax. Until recently, the only games in which minimax was known to perform poorly were games which were mainly of theoretical interest. However, this paper reports results showing poor performance of minimax in a more common game called kalah. For the kalah games tested, a… ▽ More The discovery that the minimax decision rule performs poorly in some games has sparked interest in possible alternatives to minimax. Until recently, the only games in which minimax was known to perform poorly were games which were mainly of theoretical interest. However, this paper reports results showing poor performance of minimax in a more common game called kalah. For the kalah games tested, a non-minimax decision rule called the product rule performs significantly better than minimax. This paper also discusses a possible way to predict whether or not minimax will perform well in a game when compared to product. A parameter called the rate of heuristic flaw (rhf) has been found to correlate positively with the. performance of product against minimax. Both analytical and experimental results are given that appear to support the predictive power of rhf. △ Less

Submitted 27 March, 2013; originally announced April 2013.

Comments: Appears in Proceedings of the Second Conference on Uncertainty in Artificial Intelligence (UAI1986)

Report number: UAI-P-1986-PG-49-56