arXiv subjects

Ke Li

Publications and source records attributed to Ke Li.

At least 217 records · Page 12Linked to original sources

arXiv2024

MMICT: Boosting Multi-Modal Fine-Tuning with In-Context Examples

Although In-Context Learning (ICL) brings remarkable performance gains to Large Language Models (LLMs), the improvements remain lower than fine-tuning on downstream tasks. This paper introduces Multi-Modal In-Context Tuning (MMICT), a novel multi-modal fine-tuning paradigm that boosts multi-modal fine-tuning by fully leveraging the promising ICL capability of multi-modal LLMs (MM-LLMs). We propose the Multi-Modal Hub (M-Hub), a unified module that captures various multi-modal features according to different inputs and objectives. Based on M-Hub, MMICT enables MM-LLMs to learn from in-context visual-guided textual features and subsequently generate outputs conditioned on the textual-guided visual features. Moreover, leveraging the flexibility of M-Hub, we design a variety of in-context demonstrations. Extensive experiments on a diverse range of downstream multi-modal tasks demonstrate that MMICT significantly outperforms traditional fine-tuning strategy and the vanilla ICT method that directly takes the concatenation of all information from different modalities as input. Our implementation is available at: https://github.com/KDEGroup/MMICT.

cs.AI↗

arXiv2024

EchoGuide: Active Acoustic Guidance for LLM-Based Eating Event Analysis from Egocentric Videos

Self-recording eating behaviors is a step towards a healthy lifestyle recommended by many health professionals. However, the current practice of manually recording eating activities using paper records or smartphone apps is often unsustainable and inaccurate. Smart glasses have emerged as a promising wearable form factor for tracking eating behaviors, but existing systems primarily identify when eating occurs without capturing details of the eating activities (E.g., what is being eaten). In this paper, we present EchoGuide, an application and system pipeline that leverages low-power active acoustic sensing to guide head-mounted cameras to capture egocentric videos, enabling efficient and detailed analysis of eating activities. By combining active acoustic sensing for eating detection with video captioning models and large-scale language models for retrieval augmentation, EchoGuide intelligently clips and analyzes videos to create concise, relevant activity records on eating. We evaluated EchoGuide with 9 participants in naturalistic settings involving eating activities, demonstrating high-quality summarization and significant reductions in video data needed, paving the way for practical, scalable eating activity tracking.

cs.HC↗

arXiv2024

A Rotational/Roto-translational Constraint Method for Condensed Matter

In condensed matter physics, particularly in perovskite materials, the rotational motion of molecules and ions is associated with important issues such as ion conduction mechanism. Constrained Molecular Dynamics (MD) simulations offer a means to separate translational, vibrational, and rotational motions, enabling the independent study of their effects. In this study, we introduce a rotational and roto-translational constraint algorithm based on the Velocity Verlet integrator, which has been implemented into a homebrew version of the CP2K package. The MD results show that our program can selectively constrain the molecules and ions in the system and support long-time MD runs. The algorithm can help the future study of important rotation related dynamic problems in condensed matter systems.

physics.chem-ph↗

arXiv2024

Towards scalable efficient on-device ASR with transfer learning

Multilingual pretraining for transfer learning significantly boosts the robustness of low-resource monolingual ASR models. This study systematically investigates three main aspects: (a) the impact of transfer learning on model performance during initial training or fine-tuning, (b) the influence of transfer learning across dataset domains and languages, and (c) the effect on rare-word recognition compared to non-rare words. Our finding suggests that RNNT-loss pretraining, followed by monolingual fine-tuning with Minimum Word Error Rate (MinWER) loss, consistently reduces Word Error Rates (WER) across languages like Italian and French. WER Reductions (WERR) reach 36.2% and 42.8% compared to monolingual baselines for MLS and in-house datasets. Out-of-domain pretraining leads to 28% higher WERR than in-domain pretraining. Both rare and non-rare words benefit, with rare words showing greater improvements with out-of-domain pretraining, and non-rare words with in-domain pretraining.

cs.CL↗

arXiv2024

Using shrinkage methods to estimate treatment effects in overlapping subgroups in randomized clinical trials with a time-to-event endpoint

In randomized controlled trials, forest plots are frequently used to investigate the homogeneity of treatment effect estimates in subgroups. However, the interpretation of subgroup-specific treatment effect estimates requires great care due to the smaller sample size of subgroups and the large number of investigated subgroups. Bayesian shrinkage methods have been proposed to address these issues, but they often focus on disjoint subgroups while subgroups displayed in forest plots are overlapping, i.e., each subject appears in multiple subgroups. In our approach, we first build a flexible Cox model based on all available observations, including categorical covariates that identify the subgroups of interest and their interactions with the treatment group variable. We explore both penalized partial likelihood estimation with a lasso or ridge penalty for treatment-by-covariate interaction terms, and Bayesian estimation with a regularized horseshoe prior. One advantage of the Bayesian approach is the ability to derive credible intervals for shrunken subgroup-specific estimates. In a second step, the Cox model is marginalized to obtain treatment effect estimates for all subgroups. We illustrate these methods using data from a randomized clinical trial in follicular lymphoma and evaluate their properties in a simulation study. In all simulation scenarios, the overall mean-squared error is substantially smaller for penalized and shrinkage estimators compared to the standard subgroup-specific treatment effect estimator but leads to some bias for heterogeneous subgroups. We recommend that subgroup-specific estimators, which are typically displayed in forest plots, are more routinely complemented by treatment effect estimators based on shrinkage methods. The proposed methods are implemented in the R package bonsaiforest.

stat.ME↗

arXiv2024

First Measurement of the $ν_e$ and $ν_μ$ Interaction Cross Sections at the LHC with FASER's Emulsion Detector

This paper presents the first results of the study of high-energy electron and muon neutrino charged-current interactions in the FASER$ν$ emulsion/tungsten detector of the FASER experiment at the LHC. A subset of the FASER$ν$ volume, which corresponds to a target mass of 128.6~kg, was exposed to neutrinos from the LHC $pp$ collisions with a centre-of-mass energy of 13.6~TeV and an integrated luminosity of 9.5 fb$^{-1}$. Applying stringent selections requiring electrons with reconstructed energy above 200~GeV, four electron neutrino interaction candidate events are observed with an expected background of $0.025^{+0.015}_{-0.010}$, leading to a statistical significance of 5.2$σ$. This is the first direct observation of electron neutrino interactions at a particle collider. Eight muon neutrino interaction candidate events are also detected, with an expected background of $0.22^{+0.09}_{-0.07}$, leading to a statistical significance of 5.7$σ$. The signal events include neutrinos with energies in the TeV range, the highest-energy electron and muon neutrinos ever detected from an artificial source. The energy-independent part of the interaction cross section per nucleon is measured over an energy range of 560--1740 GeV (520--1760 GeV) for $ν_e$ ($ν_μ$) to be $(1.2_{-0.7}^{+0.8}) \times 10^{-38}~\mathrm{cm}^{2}\,\mathrm{GeV}^{-1}$ ($(0.5\pm0.2) \times 10^{-38}~\mathrm{cm}^{2}\,\mathrm{GeV}^{-1}$), consistent with Standard Model predictions. These are the first measurements of neutrino interaction cross sections in those energy ranges.

hep-ex↗

arXiv2024

Towards Multimodal Sentiment Analysis Debiasing via Bias Purification

Multimodal Sentiment Analysis (MSA) aims to understand human intentions by integrating emotion-related clues from diverse modalities, such as visual, language, and audio. Unfortunately, the current MSA task invariably suffers from unplanned dataset biases, particularly multimodal utterance-level label bias and word-level context bias. These harmful biases potentially mislead models to focus on statistical shortcuts and spurious correlations, causing severe performance bottlenecks. To alleviate these issues, we present a Multimodal Counterfactual Inference Sentiment (MCIS) analysis framework based on causality rather than conventional likelihood. Concretely, we first formulate a causal graph to discover harmful biases from already-trained vanilla models. In the inference phase, given a factual multimodal input, MCIS imagines two counterfactual scenarios to purify and mitigate these biases. Then, MCIS can make unbiased decisions from biased observations by comparing factual and counterfactual outcomes. We conduct extensive experiments on several standard MSA benchmarks. Qualitative and quantitative results show the effectiveness of the proposed framework.

cs.CL↗

arXiv2024

Bi-Mamba+: Bidirectional Mamba for Time Series Forecasting

Long-term time series forecasting (LTSF) provides longer insights into future trends and patterns. Over the past few years, deep learning models especially Transformers have achieved advanced performance in LTSF tasks. However, LTSF faces inherent challenges such as long-term dependencies capturing and sparse semantic characteristics. Recently, a new state space model (SSM) named Mamba is proposed. With the selective capability on input data and the hardware-aware parallel computing algorithm, Mamba has shown great potential in balancing predicting performance and computational efficiency compared to Transformers. To enhance Mamba's ability to preserve historical information in a longer range, we design a novel Mamba+ block by adding a forget gate inside Mamba to selectively combine the new features with the historical features in a complementary manner. Furthermore, we apply Mamba+ both forward and backward and propose Bi-Mamba+, aiming to promote the model's ability to capture interactions among time series elements. Additionally, multivariate time series data in different scenarios may exhibit varying emphasis on intra- or inter-series dependencies. Therefore, we propose a series-relation-aware decider that controls the utilization of channel-independent or channel-mixing tokenization strategy for specific datasets. Extensive experiments on 8 real-world datasets show that our model achieves more accurate predictions compared with state-of-the-art methods.

cs.LG↗

arXiv2024

Reliability Function of Quantum Information Decoupling via the Sandwiched Rényi Divergence

Quantum information decoupling is a fundamental quantum information processing task, which also serves as a crucial tool in a diversity of topics in quantum physics. In this paper, we characterize the reliability function of catalytic quantum information decoupling, that is, the best exponential rate under which perfect decoupling is asymptotically approached. We have obtained the exact formula when the decoupling cost is below a critical value. In the situation of high cost, we provide meaningful upper and lower bounds. This result is then applied to quantum state merging, exploiting its inherent connection to decoupling. In addition, as technical tools, we derive the exact exponents for the smoothing of the conditional min-entropy and max-information, and we prove a novel bound for the convex-split lemma. Our results are given in terms of the sandwiched Rényi divergence, providing it with a new type of operational meaning in characterizing how fast the performance of quantum information tasks approaches the perfect.

quant-ph↗

arXiv2024

Strong Converse Exponent for Entanglement-Assisted Communication

We determine the exact strong converse exponent for entanglement-assisted classical communication of a quantum channel. Our main contribution is the derivation of an upper bound for the strong converse exponent which is characterized by the sandwiched Rényi divergence. It turns out that this upper bound coincides with the lower bound of Gupta and Wilde (Commun. Math. Phys. 334:867-887, 2015). Thus, the strong converse exponent follows from the combination of these two bounds. Our result has two implications. Firstly, it implies that the exponential bound for the strong converse property of quantum-feedback-assisted classical communication, derived by Cooney, Mosonyi and Wilde (Commun. Math. Phys. 344:797-829, 2016), is optimal. This answers their open question in the affirmative. Hence, we have determined the exact strong converse exponent for this problem as well. Secondly, due to an observation of Leung and Matthews, it can be easily extended to deal with the transmission of quantum information under the assistance of entanglement or quantum feedback, yielding similar results. The above findings provide, for the first time, a complete operational interpretation to the channel's sandwiched Rényi information of order $α> 1$.

quant-ph↗

arXiv2024

Is the System Message Really Important to Jailbreaks in Large Language Models?

The rapid evolution of Large Language Models (LLMs) has rendered them indispensable in modern society. While security measures are typically to align LLMs with human values prior to release, recent studies have unveiled a concerning phenomenon named "Jailbreak". This term refers to the unexpected and potentially harmful responses generated by LLMs when prompted with malicious questions. Most existing research focus on generating jailbreak prompts but system message configurations vary significantly in experiments. In this paper, we aim to answer a question: Is the system message really important for jailbreaks in LLMs? We conduct experiments in mainstream LLMs to generate jailbreak prompts with varying system messages: short, long, and none. We discover that different system messages have distinct resistances to jailbreaks. Therefore, we explore the transferability of jailbreaks across LLMs with different system messages. Furthermore, we propose the System Messages Evolutionary Algorithm (SMEA) to generate system messages that are more resistant to jailbreak prompts, even with minor changes. Through SMEA, we get a robust system messages population with little change in the length of system messages. Our research not only bolsters LLMs security but also raises the bar for jailbreaks, fostering advancements in this field of study.

cs.CL↗

arXiv2024

Detecting Complex Multi-step Attacks with Explainable Graph Neural Network

Complex multi-step attacks have caused significant damage to numerous critical infrastructures. To detect such attacks, graph neural network based methods have shown promising results by modeling the system's events as a graph. However, existing methods still face several challenges when deployed in practice. First, there is a lack of sufficient real attack data especially considering the large volume of normal data. Second, the modeling of event graphs is challenging due to their dynamic and heterogeneous nature. Third, the lack of explanation in learning models undermines the trustworthiness of such methods in production environments. To address the above challenges, in this paper, we propose an attack detection method, Trace2Vec. The approach first designs an erosion function to augment rare attack samples, and integrates them into the event graphs. Next, it models the event graphs via a continuous-time dynamic heterogeneous graph neural network. Finally, it employs the Monte Carlo tree search algorithm to identify events with greater contributions to the attack, thus enhancing the explainability of the detection result. We have implemented a prototype for Trace2Vec, and the experimental evaluations demonstrate its superior detection and explanation performance compared to existing methods.

cs.CR↗

arXiv2024

Neutrino Rate Predictions for FASER

The Forward Search Experiment (FASER) at CERN's Large Hadron Collider (LHC) has recently directly detected the first collider neutrinos. Neutrinos play an important role in all FASER analyses, either as signal or background, and it is therefore essential to understand the neutrino event rates. In this study, we update previous simulations and present prescriptions for theoretical predictions of neutrino fluxes and cross sections, together with their associated uncertainties. With these results, we discuss the potential for possible measurements that could be carried out in the coming years with the FASER neutrino data to be collected in LHC Run 3 and Run 4.

hep-ex↗

arXiv2024

PAPR in Motion: Seamless Point-level 3D Scene Interpolation

We propose the problem of point-level 3D scene interpolation, which aims to simultaneously reconstruct a 3D scene in two states from multiple views, synthesize smooth point-level interpolations between them, and render the scene from novel viewpoints, all without any supervision between the states. The primary challenge is on achieving a smooth transition between states that may involve significant and non-rigid changes. To address these challenges, we introduce "PAPR in Motion", a novel approach that builds upon the recent Proximity Attention Point Rendering (PAPR) technique, which can deform a point cloud to match a significantly different shape and render a visually coherent scene even after non-rigid deformations. Our approach is specifically designed to maintain the temporal consistency of the geometric structure by introducing various regularization techniques for PAPR. The result is a method that can effectively bridge large scene changes and produce visually coherent and temporally smooth interpolations in both geometry and appearance. Evaluation across diverse motion types demonstrates that "PAPR in Motion" outperforms the leading neural renderer for dynamic scenes. For more results and code, please visit our project website at https://niopeng.github.io/PAPR-in-Motion/ .

cs.CV↗

arXiv2024

Operational Interpretation of the Sandwiched Rényi Divergence of Order 1/2 to 1 as Strong Converse Exponents

We provide the sandwiched Rényi divergence of order $α\in(\frac{1}{2},1)$, as well as its induced quantum information quantities, with an operational interpretation in the characterization of the exact strong converse exponents of quantum tasks. Specifically, we consider (a) smoothing of the max-relative entropy, (b) quantum privacy amplification, and (c) quantum information decoupling. We solve the problem of determining the exact strong converse exponents for these three tasks, with the performance being measured by the fidelity or purified distance. The results are given in terms of the sandwiched Rényi divergence of order $α\in(\frac{1}{2},1)$, and its induced quantum Rényi conditional entropy and quantum Rényi mutual information. This is the first time to find the precise operational meaning for the sandwiched Rényi divergence with Rényi parameter in the interval $α\in(\frac{1}{2},1)$.

quant-ph↗

arXiv2024

On the Hyperparameter Loss Landscapes of Machine Learning Models: An Exploratory Study

Previous efforts on hyperparameter optimization (HPO) of machine learning (ML) models predominately focus on algorithmic advances, yet little is known about the topography of the underlying hyperparameter (HP) loss landscape, which plays a fundamental role in governing the search process of HPO. While several works have conducted fitness landscape analysis (FLA) on various ML systems, they are limited to properties of isolated landscape without interrogating the potential structural similarities among them. The exploration of such similarities can provide a novel perspective for understanding the mechanism behind modern HPO methods, but has been missing, possibly due to the expensive cost of large-scale landscape construction, and the lack of effective analysis methods. In this paper, we mapped 1,500 HP loss landscapes of 6 representative ML models on 63 datasets across different fidelity levels, with 11M+ configurations. By conducting exploratory analysis on these landscapes with fine-grained visualizations and dedicated FLA metrics, we observed a similar landscape topography across a wide range of models, datasets, and fidelities, and shed light on several central topics in HPO.

cs.LG↗

arXiv2024

The Solar Origin of an Intense Geomagnetic Storm on 2023 December 1st: Successive Slipping and Eruption of Multiple Magnetic Flux Ropes

The solar eruption that occurred on 2023 November 28 (SOL2023-11-28) triggered an intense geomagnetic storm on Earth on 2023 December 1. The associated Earth's auroras manifested at the most southern latitudes in the northern hemisphere observed in the past two decades. In order to explore the profound geoeffectiveness of this event, we conducted a comprehensive analysis of its solar origin to offer potential factors contributing to its impact. Magnetic flux ropes (MFRs) are twisted magnetic structures recognized as significant contributors to coronal mass ejections (CMEs), thereby impacting space weather greatly. In this event, we identified multiple MFRs in the solar active region and observed distinct slipping processes of the three MFRs: MFR1, MFR2, and MFR3. All three MFRs exhibit slipping motions at a speed of 40--137 km s$^{-1}$, extending beyond their original locations. Notably, the slipping of MFR2 extends to $\sim$30 Mm and initiate the eruption of MFR3. Ultimately, MFR1's eruption results in an M3.4-class flare and a CME, while MFR2 and MFR3 collectively produce an M9.8-class flare and another halo CME. This study shows the slipping process in a multi-MFR system, showing how one MFR's slipping can trigger the eruption of another MFR. We propose that the CME--CME interactions caused by multiple MFR eruptions may contribute to the significant geoeffectiveness.

astro-ph.SR↗

arXiv2024

Multi-Modal Prompt Learning on Blind Image Quality Assessment

Image Quality Assessment (IQA) models benefit significantly from semantic information, which allows them to treat different types of objects distinctly. Currently, leveraging semantic information to enhance IQA is a crucial research direction. Traditional methods, hindered by a lack of sufficiently annotated data, have employed the CLIP image-text pretraining model as their backbone to gain semantic awareness. However, the generalist nature of these pre-trained Vision-Language (VL) models often renders them suboptimal for IQA-specific tasks. Recent approaches have attempted to address this mismatch using prompt technology, but these solutions have shortcomings. Existing prompt-based VL models overly focus on incremental semantic information from text, neglecting the rich insights available from visual data analysis. This imbalance limits their performance improvements in IQA tasks. This paper introduces an innovative multi-modal prompt-based methodology for IQA. Our approach employs carefully crafted prompts that synergistically mine incremental semantic information from both visual and linguistic data. Specifically, in the visual branch, we introduce a multi-layer prompt structure to enhance the VL model's adaptability. In the text branch, we deploy a dual-prompt scheme that steers the model to recognize and differentiate between scene category and distortion type, thereby refining the model's capacity to assess image quality. Our experimental findings underscore the effectiveness of our method over existing Blind Image Quality Assessment (BIQA) approaches. Notably, it demonstrates competitive performance across various datasets. Our method achieves Spearman Rank Correlation Coefficient (SRCC) values of 0.961(surpassing 0.946 in CSIQ) and 0.941 (exceeding 0.930 in KADID), illustrating its robustness and accuracy in diverse contexts.

cs.CV↗