arXiv subjects

Miao Liu

Publications and source records attributed to Miao Liu.

At least 73 records · Page 4Linked to original sources

arXiv2025

Increasing Downshifting Luminescence Intensity Through an Extended Active Layer

The near-infrared (NIR) emission of rare-earth doped nanoparticles (RENPs), known as downshifting luminescence, has been extensively investigated in diverse applications from information technology to biomedicine. In promoting brightness and enriching the functionalities of the downshifting luminescence of RENPs, numerous studies have exploited inert shell to protect rare-earth dopants from surface quenchers. However, internal concentration quenching remains an unsolved puzzle when using higher dopant concentrations of rare-earth ions in an attempt to obtain brighter emission. Following a plethora of research involving core-shell structures, the interface has shown to be controllable, ranging from a well-defined, abrupt boundary to an obscure one with cation intermixing. By utilizing this inter-mixed core-shell property for the first time, we design a new architecture to create a homogeneous double-layer core-shell interface to extend the active layer, allowing more luminescent centers without severe concentration quenching. By systematically deploying the crystallinity of the starting core, shell growth dynamics, and dopant concentrations, the downshifting luminescence intensity of new archictecture achieves a 12-fold enhancement surpassing the traditional core-shell structure. These results provide deeper insight into the potential benefits of the intermixed core-shell structure, offering an effective approach to tackling the internal concentration quenching effect for highly boosted NIR optical performance.

cond-mat.mtrl-sci↗

arXiv2025

Evaluating the Prompt Steerability of Large Language Models

Building pluralistic AI requires designing models that are able to be shaped to represent a wide range of value systems and cultures. Achieving this requires first being able to evaluate the degree to which a given model is capable of reflecting various personas. To this end, we propose a benchmark for evaluating the steerability of model personas as a function of prompting. Our design is based on a formal definition of prompt steerability, which analyzes the degree to which a model's joint behavioral distribution can be shifted from its baseline. By defining steerability indices and inspecting how these indices change as a function of steering effort, we can estimate the steerability of a model across various persona dimensions and directions. Our benchmark reveals that the steerability of many current models is limited -- due to both a skew in their baseline behavior and an asymmetry in their steerability across many persona dimensions. We release an implementation of our benchmark at https://github.com/IBM/prompt-steering.

cs.CL↗

arXiv2025

Human-inspired Perspectives: A Survey on AI Long-term Memory

With the rapid advancement of AI systems, their abilities to store, retrieve, and utilize information over the long term - referred to as long-term memory - have become increasingly significant. These capabilities are crucial for enhancing the performance of AI systems across a wide range of tasks. However, there is currently no comprehensive survey that systematically investigates AI's long-term memory capabilities, formulates a theoretical framework, and inspires the development of next-generation AI long-term memory systems. This paper begins by introducing the mechanisms of human long-term memory, then explores AI long-term memory mechanisms, establishing a mapping between the two. Based on the mapping relationships identified, we extend the current cognitive architectures and propose the Cognitive Architecture of Self-Adaptive Long-term Memory (SALM). SALM provides a theoretical framework for the practice of AI long-term memory and holds potential for guiding the creation of next-generation long-term memory driven AI systems. Finally, we delve into the future directions and application prospects of AI long-term memory.

cs.AI↗

arXiv2024

Accelerating Multimodal Large Language Models by Searching Optimal Vision Token Reduction

Prevailing Multimodal Large Language Models (MLLMs) encode the input image(s) as vision tokens and feed them into the language backbone, similar to how Large Language Models (LLMs) process the text tokens. However, the number of vision tokens increases quadratically as the image resolutions, leading to huge computational costs. In this paper, we consider improving MLLM's efficiency from two scenarios, (I) Reducing computational cost without degrading the performance. (II) Improving the performance with given budgets. We start with our main finding that the ranking of each vision token sorted by attention scores is similar in each layer except the first layer. Based on it, we assume that the number of essential top vision tokens does not increase along layers. Accordingly, for Scenario I, we propose a greedy search algorithm (G-Search) to find the least number of vision tokens to keep at each layer from the shallow to the deep. Interestingly, G-Search is able to reach the optimal reduction strategy based on our assumption. For Scenario II, based on the reduction strategy from G-Search, we design a parametric sigmoid function (P-Sigmoid) to guide the reduction at each layer of the MLLM, whose parameters are optimized by Bayesian Optimization. Extensive experiments demonstrate that our approach can significantly accelerate those popular MLLMs, e.g. LLaVA, and InternVL2 models, by more than $2 \times$ without performance drops. Our approach also far outperforms other token reduction methods when budgets are limited, achieving a better trade-off between efficiency and effectiveness.

cs.CV↗

arXiv2024

Unleashing In-context Learning of Autoregressive Models for Few-shot Image Manipulation

Text-guided image manipulation has experienced notable advancement in recent years. In order to mitigate linguistic ambiguity, few-shot learning with visual examples has been applied for instructions that are underrepresented in the training set, or difficult to describe purely in language. However, learning from visual prompts requires strong reasoning capability, which diffusion models are struggling with. To address this issue, we introduce a novel multi-modal autoregressive model, dubbed $\textbf{InstaManip}$, that can $\textbf{insta}$ntly learn a new image $\textbf{manip}$ulation operation from textual and visual guidance via in-context learning, and apply it to new query images. Specifically, we propose an innovative group self-attention mechanism to break down the in-context learning process into two separate stages -- learning and applying, which simplifies the complex problem into two easier tasks. We also introduce a relation regularization method to further disentangle image transformation features from irrelevant contents in exemplar images. Extensive experiments suggest that our method surpasses previous few-shot image manipulation models by a notable margin ($\geq$19% in human evaluation). We also find our model can be further boosted by increasing the number or diversity of exemplar images.

cs.CV↗

arXiv2024

OpenLS-DGF: An Adaptive Open-Source Dataset Generation Framework for Machine Learning Tasks in Logic Synthesis

This paper introduces OpenLS-DGF, an adaptive logic synthesis dataset generation framework, to enhance machine learning~(ML) applications within the logic synthesis process. Previous dataset generation flows were tailored for specific tasks or lacked integrated machine learning capabilities. While OpenLS-DGF supports various machine learning tasks by encapsulating the three fundamental steps of logic synthesis: Boolean representation, logic optimization, and technology mapping. It preserves the original information in both Verilog and machine-learning-friendly GraphML formats. The verilog files offer semi-customizable capabilities, enabling researchers to insert additional steps and incrementally refine the generated dataset. Furthermore, OpenLS-DGF includes an adaptive circuit engine that facilitates the final dataset management and downstream tasks. The generated OpenLS-D-v1 dataset comprises 46 combinational designs from established benchmarks, totaling over 966,000 Boolean circuits. OpenLS-D-v1 supports integrating new data features, making it more versatile for new challenges. This paper demonstrates the versatility of OpenLS-D-v1 through four distinct downstream tasks: circuit classification, circuit ranking, quality of results (QoR) prediction, and probability prediction. Each task is chosen to represent essential steps of logic synthesis, and the experimental results show the generated dataset from OpenLS-DGF achieves prominent diversity and applicability. The source code and datasets are available at https://github.com/Logic-Factory/ACE/blob/master/OpenLS-DGF/readme.md.

cs.AI↗

arXiv2024

Asymptotically sharp bounds for cancellative and union-free hypergraphs

An $r$-graph is called $t$-cancellative if for arbitrary $t+2$ distinct edges $A_1,\ldots,A_t,B,C$, it holds that $(\cup_{i=1}^t A_i)\cup B\neq (\cup_{i=1}^t A_i)\cup C$; it is called $t$-union-free if for arbitrary two distinct subsets $\mathcal{A},\mathcal{B}$, each consisting of at most $t$ edges, it holds that $\cup_{A\in\mathcal{A}} A\neq \cup_{B\in\mathcal{B}} B$. Let $C_t(n,r)$ and $U_t(n,r)$ denote the maximum number of edges that can be contained in an $n$-vertex $t$-cancellative and $t$-union-free $r$-graph, respectively. The study of $C_t(n,r)$ and $U_t(n,r)$ has a long history, dating back to the classic works of Erdős and Katona, and Erdős and Moser in the 1970s. In 2020, Shangguan and Tamo showed that $C_{2(t-1)}(n,tk)=Θ(n^k)$ and $U_{t+1}(n,tk)=Θ(n^k)$ for all $t\ge 2$ and $k\ge 2$. In this paper, we determine the asymptotics of these two functions up to a lower order term, by showing that for all $t\ge 2$ and $k\ge 2$, \begin{align*} \text{$\lim_{n\rightarrow\infty}\frac{C_{2(t-1)}(n,tk)}{n^k}=\lim_{n\rightarrow\infty}\frac{U_{t+1}(n,tk)}{n^k}=\frac{1}{k!}\cdot \frac{1}{\binom{tk-1}{k-1}}$.} \end{align*} Previously, it was only known by a result of Füredi in 2012 that $\lim_{n\rightarrow\infty}\frac{C_{2}(n,4)}{n^2}=\frac{1}{6}$. To prove the lower bounds of the limits, we utilize a powerful framework developed recently by Delcourt and Postle, and independently by Glock, Joos, Kim, Kühn, and Lichev, which shows the existence of near-optimal hypergraph packings avoiding certain small configurations, and to prove the upper bounds, we apply a novel counting argument that connects $C_{2(t-1)}(n,tk)$ to a classic result of Kleitman and Frankl on a special case of the famous Erdős Matching Conjecture.

math.CO↗

arXiv2024

Human Action Anticipation: A Survey

Predicting future human behavior is an increasingly popular topic in computer vision, driven by the interest in applications such as autonomous vehicles, digital assistants and human-robot interactions. The literature on behavior prediction spans various tasks, including action anticipation, activity forecasting, intent prediction, goal prediction, and so on. Our survey aims to tie together this fragmented literature, covering recent technical innovations as well as the development of new large-scale datasets for model training and evaluation. We also summarize the widely-used metrics for different tasks and provide a comprehensive performance comparison of existing approaches on eleven action anticipation datasets. This survey serves as not only a reference for contemporary methodologies in action anticipation, but also a guideline for future research direction of this evolving landscape.

cs.CV↗

arXiv2024

In the Eye of Transformer: Global-Local Correlation for Egocentric Gaze Estimation

In this paper, we present the first transformer-based model to address the challenging problem of egocentric gaze estimation. We observe that the connection between the global scene context and local visual information is vital for localizing the gaze fixation from egocentric video frames. To this end, we design the transformer encoder to embed the global context as one additional visual token and further propose a novel Global-Local Correlation (GLC) module to explicitly model the correlation of the global token and each local token. We validate our model on two egocentric video datasets - EGTEA Gaze+ and Ego4D. Our detailed ablation studies demonstrate the benefits of our method. In addition, our approach exceeds previous state-of-the-arts by a large margin. We also provide additional visualizations to support our claim that global-local correlation serves a key representation for predicting gaze fixation from egocentric videos. More details can be found in our website (https://bolinlai.github.io/GLC-EgoGazeEst).

cs.CV↗

arXiv2024

Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectives

We present Ego-Exo4D, a diverse, large-scale multimodal multiview video dataset and benchmark challenge. Ego-Exo4D centers around simultaneously-captured egocentric and exocentric video of skilled human activities (e.g., sports, music, dance, bike repair). 740 participants from 13 cities worldwide performed these activities in 123 different natural scene contexts, yielding long-form captures from 1 to 42 minutes each and 1,286 hours of video combined. The multimodal nature of the dataset is unprecedented: the video is accompanied by multichannel audio, eye gaze, 3D point clouds, camera poses, IMU, and multiple paired language descriptions -- including a novel "expert commentary" done by coaches and teachers and tailored to the skilled-activity domain. To push the frontier of first-person video understanding of skilled human activity, we also present a suite of benchmark tasks and their annotations, including fine-grained activity understanding, proficiency estimation, cross-view translation, and 3D hand/body pose. All resources are open sourced to fuel new research in the community. Project page: http://ego-exo4d-data.org/

cs.CV↗

arXiv2024

Model-in-the-Loop (MILO): Accelerating Multimodal AI Data Annotation with LLMs

The growing demand for AI training data has transformed data annotation into a global industry, but traditional approaches relying on human annotators are often time-consuming, labor-intensive, and prone to inconsistent quality. We propose the Model-in-the-Loop (MILO) framework, which integrates AI/ML models into the annotation process. Our research introduces a collaborative paradigm that leverages the strengths of both professional human annotators and large language models (LLMs). By employing LLMs as pre-annotation and real-time assistants, and judges on annotator responses, MILO enables effective interaction patterns between human annotators and LLMs. Three empirical studies on multimodal data annotation demonstrate MILO's efficacy in reducing handling time, improving data quality, and enhancing annotator experiences. We also introduce quality rubrics for flexible evaluation and fine-grained feedback on open-ended annotations. The MILO framework has implications for accelerating AI/ML development, reducing reliance on human annotation alone, and promoting better alignment between human and machine values.

cs.HC↗

arXiv2024

SF-DQN: Provable Knowledge Transfer using Successor Feature for Deep Reinforcement Learning

This paper studies the transfer reinforcement learning (RL) problem where multiple RL problems have different reward functions but share the same underlying transition dynamics. In this setting, the Q-function of each RL problem (task) can be decomposed into a successor feature (SF) and a reward mapping: the former characterizes the transition dynamics, and the latter characterizes the task-specific reward function. This Q-function decomposition, coupled with a policy improvement operator known as generalized policy improvement (GPI), reduces the sample complexity of finding the optimal Q-function, and thus the SF \& GPI framework exhibits promising empirical performance compared to traditional RL methods like Q-learning. However, its theoretical foundations remain largely unestablished, especially when learning the successor features using deep neural networks (SF-DQN). This paper studies the provable knowledge transfer using SFs-DQN in transfer RL problems. We establish the first convergence analysis with provable generalization guarantees for SF-DQN with GPI. The theory reveals that SF-DQN with GPI outperforms conventional RL approaches, such as deep Q-network, in terms of both faster convergence rate and better generalization. Numerical experiments on real and synthetic RL tasks support the superior performance of SF-DQN \& GPI, aligning with our theoretical findings.

cs.LG↗

arXiv2024

Chemical versus physical pressure effects on the structure transition of bilayer nickelates

The observation of high-$T_c$ superconductivity (HTSC) in concomitant with pressure-induced orthorhombic-tetragonal structural transition in the bilayer La$_{3}$Ni$_2$O$_7$ has sparked hopes of achieving HTSC by stabilizing the tetragonal phase at ambient pressure. To mimic the effect of external physical pressures, the application of chemical pressure via replacing La$^3$$^+$ with smaller rare-earth R$^3$$^+$ has been considered as a potential route. Here we clarify the distinct effects of chemical and physical pressures on the structural transition of bilayer nickelates through a combined experimental and theoretical investigation. Contrary to general expectations, we find that substitutions of smaller R$^3$$^+$ for La$^3$$^+$ in La$_{3-x}$R$_x$Ni$_2$O$_{7-δ}$, despite of an overall lattice contraction, produce stronger orthorhombic structural distortions and thus require higher pressures to induce the structural transition. We established a quantitative relationship between the critical pressure $P_c$ for structural transition and the average size of $A$-site cations. A linear extrapolation of $P_c$ versus <$r_A$> yields a putative critical value of <$r_A$>$_c$ ~ 1.23 angstrom for $P_c$ ~ 1 bar. The negative correlation between $P_c$ and <$r_A$> indicates that it is unlikely to reduce $P_c$ to ambient by replacing La$^3$$^+$ with smaller R$^3$$^+$ ions. Instead, partial substitution of La$^3$$^+$ with larger cations such as alkaline-earth Sr$^2$$^+$ or Ba$^2$$^+$ might be a feasible approach. Our results provide valuable guidelines in the quest of ambient-pressure HTSC in bilayer nickelates.

cond-mat.str-el↗

arXiv2024

Benchmarking for Deep Uplift Modeling in Online Marketing

Online marketing is critical for many industrial platforms and business applications, aiming to increase user engagement and platform revenue by identifying corresponding delivery-sensitive groups for specific incentives, such as coupons and bonuses. As the scale and complexity of features in industrial scenarios increase, deep uplift modeling (DUM) as a promising technique has attracted increased research from academia and industry, resulting in various predictive models. However, current DUM still lacks some standardized benchmarks and unified evaluation protocols, which limit the reproducibility of experimental results in existing studies and the practical value and potential impact in this direction. In this paper, we provide an open benchmark for DUM and present comparison results of existing models in a reproducible and uniform manner. To this end, we conduct extensive experiments on two representative industrial datasets with different preprocessing settings to re-evaluate 13 existing models. Surprisingly, our experimental results show that the most recent work differs less than expected from traditional work in many cases. In addition, our experiments also reveal the limitations of DUM in generalization, especially for different preprocessing and test distributions. Our benchmarking work allows researchers to evaluate the performance of new models quickly but also reasonably demonstrates fair comparison results with existing models. It also gives practitioners valuable insights into often overlooked considerations when deploying DUM. We will make this benchmarking library, evaluation protocol, and experimental setup available on GitHub.

cs.LG↗

arXiv2024

Context-Former: Stitching via Latent Conditioned Sequence Modeling

Offline reinforcement learning (RL) algorithms can learn better decision-making compared to behavior policies by stitching the suboptimal trajectories to derive more optimal ones. Meanwhile, Decision Transformer (DT) abstracts the RL as sequence modeling, showcasing competitive performance on offline RL benchmarks. However, recent studies demonstrate that DT lacks of stitching capacity, thus exploiting stitching capability for DT is vital to further improve its performance. In order to endow stitching capability to DT, we abstract trajectory stitching as expert matching and introduce our approach, ContextFormer, which integrates contextual information-based imitation learning (IL) and sequence modeling to stitch sub-optimal trajectory fragments by emulating the representations of a limited number of expert trajectories. To validate our approach, we conduct experiments from two perspectives: 1) We conduct extensive experiments on D4RL benchmarks under the settings of IL, and experimental results demonstrate ContextFormer can achieve competitive performance in multiple IL settings. 2) More importantly, we conduct a comparison of ContextFormer with various competitive DT variants using identical training datasets. The experimental results unveiled ContextFormer's superiority, as it outperformed all other variants, showcasing its remarkable performance.

cs.LG↗

arXiv2024

BEHAVIOR Vision Suite: Customizable Dataset Generation via Simulation

The systematic evaluation and understanding of computer vision models under varying conditions require large amounts of data with comprehensive and customized labels, which real-world vision datasets rarely satisfy. While current synthetic data generators offer a promising alternative, particularly for embodied AI tasks, they often fall short for computer vision tasks due to low asset and rendering quality, limited diversity, and unrealistic physical properties. We introduce the BEHAVIOR Vision Suite (BVS), a set of tools and assets to generate fully customized synthetic data for systematic evaluation of computer vision models, based on the newly developed embodied AI benchmark, BEHAVIOR-1K. BVS supports a large number of adjustable parameters at the scene level (e.g., lighting, object placement), the object level (e.g., joint configuration, attributes such as "filled" and "folded"), and the camera level (e.g., field of view, focal length). Researchers can arbitrarily vary these parameters during data generation to perform controlled experiments. We showcase three example application scenarios: systematically evaluating the robustness of models across different continuous axes of domain shift, evaluating scene understanding models on the same set of images, and training and evaluating simulation-to-real transfer for a novel vision task: unary and binary state prediction. Project website: https://behavior-vision-suite.github.io/

cs.CV↗

arXiv2024

The Audio-Visual Conversational Graph: From an Egocentric-Exocentric Perspective

In recent years, the thriving development of research related to egocentric videos has provided a unique perspective for the study of conversational interactions, where both visual and audio signals play a crucial role. While most prior work focus on learning about behaviors that directly involve the camera wearer, we introduce the Ego-Exocentric Conversational Graph Prediction problem, marking the first attempt to infer exocentric conversational interactions from egocentric videos. We propose a unified multi-modal framework -- Audio-Visual Conversational Attention (AV-CONV), for the joint prediction of conversation behaviors -- speaking and listening -- for both the camera wearer as well as all other social partners present in the egocentric video. Specifically, we adopt the self-attention mechanism to model the representations across-time, across-subjects, and across-modalities. To validate our method, we conduct experiments on a challenging egocentric video dataset that includes multi-speaker and multi-conversation scenarios. Our results demonstrate the superior performance of our method compared to a series of baselines. We also present detailed ablation studies to assess the contribution of each component in our model. Check our project page at https://vjwq.github.io/AV-CONV/.

cs.CV↗

arXiv2024

Strong electron-phonon coupling in Ba$_{1-x}$Sr$_x$Ni$_2$As$_2$

The charge density wave (CDW) or nematicity has been found to coexist with superconductivity in many systems. It is thus interesting that the superconducting transition temperature $T_c$ in the doped BaNi$_2$As$_2$ system can be enhanced up to six times as the CDW or nematicity in the undoped compound is suppressed. Here we show that the transverse acoustic phonons of Ba$_{1-x}$Sr$_x$Ni$_2$As$_2$ are strongly damped in a wide doping range and over the whole $Q$ range, which excludes its origin from either CDW or nematicity. The damping of TA phonons can be understood as large electron-phonon coupling and possible strong hybridization between acoustic and optical phonons as shown by the first-principle calculations. The superconductivity can be quantitatively reproduced by the change of electron-phonon coupling constant calculated by the McMillan equation in the BCS framework, which suggests that no quantum fluctuations of any order is needed to promote the superconductivity. On the contrary, the change of $T_c$ in this system should be understood as the six-fold suppression of superconductivity in undoped compounds.

cond-mat.supr-con↗