Search Results for author:
Found 55 papers, 14 papers with code
Tencent submission for WMT20 Quality Estimation Shared Task
This paper presents Tencent’s submission to the WMT20 Quality Estimation (QE) Shared Task: Sentence-Level Post-editing Effort for English-Chinese in Task 2.
Learning Compositional Functions with Transformers from Easy-to-Hard Data
Towards answering this question, in this work we study the learnability of the $k$-fold composition task, which requires computing an interleaved composition of $k$ input permutations and $k$ hidden permutations, and can be expressed by a transformer with $O(\log k)$ layers.
Beyond Words: Augmenting Discriminative Richness via Diffusions in Unsupervised Prompt Learning
Fine-tuning vision-language models (VLMs) with large amounts of unlabeled data has recently garnered significant interest.
Cross-Document Cross-Lingual NLI via RST-Enhanced Graph Fusion and Interpretability Prediction
Our work sheds light on the study of NLI and will bring research interest on cross-document cross-lingual context understanding, hallucination elimination and interpretability inference.
Neural Encoding and Decoding at Scale
Altogether, our approach is a step towards a foundation model of the brain that enables seamless translation between neural activity and behavior.
Training-free Dense-Aligned Diffusion Guidance for Modular Conditional Image Synthesis
For the drag condition, we introduce a Dense Motion Alignment (DMA) module to apply multi-level motion regularization, ensuring that each pixel follows its desired trajectory without visual artifacts.
Fin-R1: A Large Language Model for Financial Reasoning through Reinforcement Learning
Reasoning large language models are rapidly evolving across various domains.
What Makes a Reward Model a Good Teacher? An Optimization Perspective
First, we prove that regardless of how accurate a reward model is, if it induces low reward variance, then the RLHF objective suffers from a flat landscape.
ReelWave: Multi-Agentic Movie Sound Generation through Multimodal LLM Conversation
To address on-screen sound generation, after detecting any talking humans in videos, we capture semantically and temporally synchronized sound by training a prediction model that forecasts interpretable, time-varying audio control signals: loudness, pitch, and timbre, which are used by a Foley Artist agent to condition a cross-attention module in the sound generation.
Dyads: Artist-Centric, AI-Generated Dance Duets
Existing AI-generated dance methods primarily train on motion capture data from solo dance performances, but a critical feature of dance in nearly any genre is the interaction of two or more bodies in space.
Invisible Strings: Revealing Latent Dancer-to-Dancer Interactions with Graph Neural Networks
Dancing in a duet often requires a heightened attunement to one's partner: their orientation in space, their momentum, and the forces they exert on you.
ZiGong 1.0: A Large Language Model for Financial Credit
Large Language Models (LLMs) have demonstrated strong performance across various general Natural Language Processing (NLP) tasks.
Humanity's Last Exam
However, benchmarks are not keeping pace in difficulty: LLMs now achieve over 90\% accuracy on popular benchmarks like MMLU, limiting informed measurement of state-of-the-art LLM capabilities.
Ranked #4 on
Humanity's Last Exam
on Humanity's Last Exam
Class Incremental Fault Diagnosis under Limited Fault Data via Supervised Contrastive Knowledge Distillation
Class-incremental fault diagnosis requires a model to adapt to new fault classes while retaining previous knowledge.
SeMi: When Imbalanced Semi-Supervised Learning Meets Mining Hard Examples
This method distinguishes the entropy differences among logits of hard and easy examples, thereby identifying hard examples and increasing the utility of unlabeled data, better addressing the imbalance problem in CISSL.
Analysis of Higher-Order Ising Hamiltonians
It is challenging to scale Ising machines for industrial-level problems due to algorithm or hardware limitations.
Learning and Transferring Sparse Contextual Bigrams with Linear Transformers
Transformers have excelled in natural language modeling and one reason behind this success is their exceptional ability to combine contextual informal and global knowledge.
Optimizing Transformer based on high-performance optimizer for predicting employment sentiment in American social media content
This social media based data analysis method can not only capture social dynamics in a timely manner, but also promote decision-makers to pay attention to public concerns and provide data support for improving employment conditions.
Audio-Agent: Leveraging LLMs For Audio Generation, Editing and Composition
For video-to-audio (VTA) tasks, most existing methods require training a timestamp detector to synchronize video events with the generated audio, a process that can be tedious and time-consuming.
CPFD: Confidence-aware Privileged Feature Distillation for Short Video Classification
To integrate both features while maintaining efficiency and manageable resource costs, we present Confidence-aware Privileged Feature Distillation (CPFD), which empowers features of an end-to-end multi-modal model by adaptively distilling privileged features during training.
KARMA: Augmenting Embodied AI Agents with Long-and-short Term Memory Systems
Compared to state-of-the-art embodied agents enhanced with memory, our memory-augmented embodied AI agent improves success rates by 1. 3x and 2. 3x in Composite Tasks and Complex Tasks within the AI2-THOR simulator, respectively, and enhances task execution efficiency by 3. 4x and 62. 7x.
DanceCamAnimator: Keyframe-Based Controllable 3D Dance Camera Synthesis
Unlike human movements, which are always continuous, dance camera movements involve both continuous sequences of variable lengths and sudden drastic changes to simulate the switching of multiple cameras.
Improved Unet model for brain tumor image segmentation based on ASPP-coordinate attention mechanism
Finally, we apply the trained traditional Unet model and the improved Unet model based on the coordinate attention mechanism and ASPP module to the test set for brain tumor image segmentation prediction.
CoPRA: Bridging Cross-domain Pretrained Sequence Models with Complex Structures for Protein-RNA Binding Affinity Prediction
We propose a Co-Former to combine the cross-modal sequence and structure information and a bi-scope pre-training strategy for improving Co-Former's interaction understanding.
FocusLLM: Precise Understanding of Long Context by Dynamic Condensing
FocusLLM stands out for great training efficiency and versatility: trained with an 8K input length and with much less training cost than previous methods, FocusLLM exhibits superior performance across downstream tasks and maintains strong language modeling ability when handling extensive long texts, even up to 400K tokens.
SA-GDA: Spectral Augmentation for Graph Domain Adaptation
Following the observation, we align the category feature space of different domains in the spectral domain instead of aligning the whole features space, and we theoretical proof the stability of proposed \method{}.
FTF-ER: Feature-Topology Fusion-Based Experience Replay Method for Continual Graph Learning
Specifically, from an overall perspective to maximize the utilization of the entire graph data, we propose a highly complementary approach including both feature and global topological information, which can significantly improve the effectiveness of the sampled nodes.
PlacidDreamer: Advancing Harmony in Text-to-3D Generation
Previous methods utilize end-to-end 3D generation models to initialize 3D Gaussians, multi-view diffusion models to enforce multi-view consistency, and text-to-image diffusion models to refine details with score distillation algorithms.
Towards a "universal translator" for neural dynamics at single-cell, single-spike resolution
Neuroscience research has made immense progress over the last decade, but our understanding of the brain remains fragmented and piecemeal: the dream of probing an arbitrary brain region and automatically reading out the information encoded in its neural activity remains out of reach.
Transformers Provably Learn Sparse Token Selection While Fully-Connected Nets Cannot
The transformer architecture has prevailed in various deep learning settings due to its exceptional capabilities to select and compose structural information.
A Multi-module Robust Method for Transient Stability Assessment against False Label Injection Cyberattacks
Leveraging the clustering assignments, we construct a training label corrector to rectify the injected false labels and progressively enhance robustness and resilience against FLI.
C3LLM: Conditional Multimodal Content Generation Using Large Language Models
C3LLM adapts the Large Language Model (LLM) structure as a bridge for aligning different modalities, synthesizing the given conditional information, and making multimodal generation in a discrete manner.
BCFPL: Binary classification ConvNet based Fast Parking space recognition with Low resolution image
The automobile plays an important role in the economic activities of mankind, especially in the metropolis.
A Generative Approach to Credit Prediction with Learnable Prompts for Multi-scale Temporal Representation Learning
Recent industrial credit scoring models remain heavily reliant on manually tuned statistical learning methods.
An Interpretable Power System Transient Stability Assessment Method with Expert Guiding Neural-Regression-Tree
TSA-ENRT utilizes an expert guiding nonlinear regression tree to approximate the neural network prediction and the neural network can be explained by the interpretive rules generated by the tree model.
DanceCamera3D: 3D Camera Movement Synthesis with Music and Dance
However, camera movement synthesis with music and dance remains an unsolved challenging problem due to the scarcity of paired data.
Generate Like Experts: Multi-Stage Font Generation by Incorporating Font Transfer Process into Diffusion Models
Based on this observation we generalize diffusion methods to model font generative process by separating the reverse diffusion process into three stages with different functions: The structure construction stage first generates the structure information for the target character based on the source image and the font transfer stage subsequently transforms the source font to the target font.
RS-DGC: Exploring Neighborhood Statistics for Dynamic Gradient Compression on Remote Sensing Image Interpretation
The key component of RS-DGC is a Neighborhood Statistical Indicator (NSI), which can quantify the importance of gradients within a specified neighborhood on each node to sparsify the local gradients before gradient transmission in each iteration.
FedDiff: Diffusion Model Driven Federated Learning for Multi-Modal and Multi-Clients
With the rapid development of imaging sensor technology in the field of remote sensing, multi-modal remote sensing data fusion has emerged as a crucial research direction for land cover classification tasks.
Recent Advances in Multi-modal 3D Scene Understanding: A Comprehensive Survey and Evaluation
Multi-modal 3D scene understanding has gained considerable attention due to its wide applications in many areas, such as autonomous driving and human-computer interaction.
Weighted Joint Maximum Mean Discrepancy Enabled Multi-Source-Multi-Target Unsupervised Domain Adaptation Fault Diagnosis
Despite the remarkable results that can be achieved by data-driven intelligent fault diagnosis techniques, they presuppose the same distribution of training and test data as well as sufficient labeled data.
FedEdge AI-TC: A Semi-supervised Traffic Classification Method based on Trusted Federated Deep Learning for Mobile Edge Computing
The framework enhances user privacy and model credibility, offering a comprehensive solution for dependable and transparent Network TC in 5G CPE, thus enhancing service quality and security.
Hard Sample Mining Enabled Supervised Contrastive Feature Learning for Wind Turbine Pitch System Fault Diagnosis
The proposed method employs cosine similarity to identify hard samples and subsequently, leverages supervised contrastive learning to learn more discriminative representations by constructing hard sample pairs.
LA3: Efficient Label-Aware AutoAugment
Automated augmentation is an emerging and effective technique to search for data augmentation policies to improve generalizability of deep neural network training.
Understanding Edge-of-Stability Training Dynamics with a Minimalist Example
Globally we observe that the training dynamics for our example has an interesting bifurcating behavior, which was also observed in the training of neural nets.
Analyzing Sharpness along GD Trajectory: Progressive Sharpening and Edge of Stability
Based on this empirical observation, we attempt to theoretically and empirically explain the dynamics of various key quantities that lead to the change of sharpness in each phase of EOS.
Explicit and implicit models in infrared and visible image fusion
Infrared and visible images, as multi-modal image pairs, show significant differences in the expression of the same scene.
Residual-guided Personalized Speech Synthesis based on Face Image
Experimental results show that the speech synthesized by our model is comparable to the personalized speech synthesized by training a large amount of audio data in previous works.
Exploiting full Resolution Feature Context for Liver Tumor and Vessel Segmentation via Integrate Framework: Application to Liver Tumor and Vessel 3D Reconstruction under embedded microprocessor
Segmentation and labeling of liver tumors and blood vessels in CT images can provide convenience for doctors in liver tumor diagnosis and surgical intervention.
Verdi: Quality Estimation and Error Detection for Bilingual Corpora
Verdi adopts two word predictors to enable diverse features to be extracted from a pair of sentences for subsequent quality estimation, including a transformer-based neural machine translation (NMT) model and a pre-trained cross-lingual language model (XLM).
Convergence of Gradient Algorithms for Nonconvex C^{1+alpha} Cost Functions
This paper is concerned with convergence of stochastic gradient algorithms with momentum terms in the nonconvex setting.
Learning Better Features for Face Detection with Feature Fusion and Segmentation Supervision
We assume that problems inside are inadequate use of supervision information and imbalance between semantics and details at all level feature maps in CNN even with Feature Pyramid Networks (FPN).
Intelligent Health Recommendation System for Computer Users
The time people spend in front of computers has been increasing steadily due to the role computers play in modern society.
Geometric VLAD for Large Scale Image Search
We present a novel compact image descriptor for large scale image search.
Who and Where: People and Location Co-Clustering
In this paper, we consider the clustering problem on images where each image contains patches in people and location domains.
