Search Results for author:
Found 58 papers, 31 papers with code
Uncertain Local-to-Global Networks for Document-Level Event Factuality Identification
Moreover, we propose an Uncertain Information Aggregation module to leverage the global structure for integrating the local information.
Beyond Prompt Content: Enhancing LLM Performance via Content-Format Integrated Prompt Optimization
Large Language Models (LLMs) have shown significant capability across various tasks, with their real-world effectiveness often driven by prompt design.
Real-Time Neural-Enhancement for Online Cloud Gaming
To address this, we introduce River, a cloud gaming delivery framework designed based on the observation that video segment features in cloud gaming are typically repetitive and redundant.
SCBench: A KV Cache-Centric Analysis of Long-Context Methods
To address these challenges, optimizations for long-context inference have been developed, centered around the KV cache.
LLM2CLIP: Powerful Language Model Unlocks Richer Visual Representation
CLIP is a foundational multimodal model that aligns image and text features into a shared space using contrastive learning on large-scale image-text pairs.
The Potential and Value of AI Chatbot in Personalized Cognitive Training
In recent years, the rapid aging of the global population has led to an increase in cognitive disorders, such as Alzheimer's disease, presenting significant public health challenges.
SPFresh: Incremental In-Place Update for Billion-Scale Vector Search
LIRE achieves low-overhead vector updates by only reassigning vectors at the boundary between partitions, where in a high-quality vector index the amount of such vectors are deemed small.
Retrieval Augmented Generation (RAG) and Beyond: A Comprehensive Survey on How to Make your LLMs use External Data More Wisely
In this survey, we propose a RAG task categorization method, classifying user queries into four levels based on the type of external data required and primary focus of the task: explicit fact queries, implicit fact queries, interpretable rationale queries, and hidden rationale queries.
RetrievalAttention: Accelerating Long-Context LLM Inference via Vector Retrieval
This paper proposes RetrievalAttention, a training-free approach to both accelerate attention computation and reduce GPU memory consumption.
Weak-to-Strong Reasoning
When large language models (LLMs) exceed human-level capabilities, it becomes increasingly challenging to provide full-scale and accurate supervision for these models.
MInference 1.0: Accelerating Pre-filling for Long-Context LLMs via Dynamic Sparse Attention
With the pattern and sparse indices, we perform efficient sparse attention calculations via our optimized GPU kernels to significantly reduce the latency in the pre-filling stage of long-context LLMs.
Expressive and Generalizable Low-rank Adaptation for Large Models via Slow Cascaded Learning
Efficient fine-tuning plays a fundamental role in modern large models, with low-rank adaptation emerging as a particularly promising approach.
VisEval: A Benchmark for Data Visualization in the Era of Large Language Models
However, the lack of a comprehensive and reliable benchmark hinders our understanding of LLMs' capabilities in visualization generation.
BeHonest: Benchmarking Honesty in Large Language Models
Building on this foundation, we designed 10 scenarios to evaluate and analyze 9 popular LLMs on the market, including both closed-source and open-source models from different model families with varied model sizes.
OlympicArena: Benchmarking Multi-discipline Cognitive Reasoning for Superintelligent AI
We delve into the models' cognitive reasoning abilities, their performance across different modalities, and their outcomes in process-level evaluations, which are vital for tasks requiring complex reasoning with lengthy solutions.
Mitigate Position Bias in Large Language Models via Scaling a Single Dimension
This paper first explores the micro-level manifestations of position bias, concluding that attention weights are a micro-level expression of position bias.
Parrot: Efficient Serving of LLM-based Applications with Semantic Variable
Public LLM services have to blindly optimize individual LLM requests, leading to sub-optimal end-to-end performance of LLM applications.
Position Engineering: Boosting Large Language Models through Positional Information Manipulation
Position engineering thus represents a promising new strategy for exploiting the capabilities of large language models.
Designing Network Algorithms via Large Language Models
We introduce NADA, the first framework to autonomously design network algorithms by leveraging the generative capabilities of large language models (LLMs).
LLMLingua-2: Data Distillation for Efficient and Faithful Task-Agnostic Prompt Compression
Additionally, our model is 3x-6x faster than existing prompt compression methods, while accelerating the end-to-end latency by 1. 6x-2. 9x with compression ratios of 2x-5x.
Automated Contrastive Learning Strategy Search for Time Series
In this paper, we present an Automated Machine Learning (AutoML) practice at Microsoft, which automatically learns CLS for time series datasets and tasks, namely Automated Contrastive Learning (AutoCL).
Benchmarking Data Science Agents
In this paper, we introduce DSEval -- a novel evaluation paradigm, as well as a series of innovative benchmarks tailored for assessing the performance of these agents throughout the entire data science lifecycle.
On the Out-Of-Distribution Generalization of Multimodal Large Language Models
We investigate the generalization boundaries of current Multimodal Large Language Models (MLLMs) via comprehensive evaluation under out-of-distribution scenarios and domain-specific tasks.
Alignment for Honesty
Recent research has made significant strides in aligning large language models (LLMs) with helpfulness and harmlessness.
CoLLiE: Collaborative Training of Large Language Models in an Efficient Way
This paper introduces CoLLiE, an efficient library that facilitates collaborative training of large language models using 3D parallelism, parameter-efficient fine-tuning (PEFT) methods, and optimizers such as Lion, Adan, Sophia, LOMO and AdaLomo.
Unified Medical Image Pre-training in Language-Guided Common Semantic Space
To overcome the aforementioned challenges, we propose an Unified Medical Image Pre-training framework, namely UniMedI, which utilizes diagnostic reports as common semantic space to create unified representations for diverse modalities of medical images (especially for 2D and 3D images).
Plan, Verify and Switch: Integrated Reasoning with Diverse X-of-Thoughts
As large language models (LLMs) have shown effectiveness with different prompting methods, such as Chain of Thought, Program of Thought, we find that these methods have formed a great complementarity to each other on math reasoning tasks.
LongLLMLingua: Accelerating and Enhancing LLMs in Long Context Scenarios via Prompt Compression
In long context scenarios, large language models (LLMs) face three main challenges: higher computational cost, performance reduction, and position bias.
LLMLingua: Compressing Prompts for Accelerated Inference of Large Language Models
Large language models (LLMs) have been applied in various applications due to their astonishing capabilities.
Enabling Real-time Neural Recovery for Cloud Gaming on Mobile Devices
Our approach is extensively evaluated using iPhone 12 and laptop implementations, and we demonstrate the utility of game states in the game video recovery and the effectiveness of our overall design.
Constraint-aware and Ranking-distilled Token Pruning for Efficient Transformer Inference
Deploying pre-trained transformer models like BERT on downstream tasks in resource-constrained scenarios is challenging due to their high inference cost, which grows rapidly with input sequence length.
Full Parameter Fine-tuning for Large Language Models with Limited Resources
Large Language Models (LLMs) have revolutionized Natural Language Processing (NLP) but demand massive GPU resources for training.
End-to-End Word-Level Pronunciation Assessment with MASK Pre-training
Pronunciation assessment is a major challenge in the computer-aided pronunciation training system, especially at the word (phoneme)-level.
Accurate and Structured Pruning for Efficient Automatic Speech Recognition
In this paper, we propose a novel compression strategy that leverages structured pruning and knowledge distillation to reduce the model size and inference cost of the Conformer model while preserving high recognition performance.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
An AMR-based Link Prediction Approach for Document-level Event Argument Extraction
Motivated by the fact that all event structures can be inferred from AMR, this work reformulates EAE as a link prediction problem on AMR graphs.
Abstract Meaning Representation
Event Argument Extraction
+2
EfficientViT: Memory Efficient Vision Transformer with Cascaded Group Attention
Comprehensive experiments demonstrate EfficientViT outperforms existing efficient models, striking a good trade-off between speed and accuracy.
Learned Focused Plenoptic Image Compression with Microimage Preprocessing and Global Attention
Also, it achieves 18. 73% bitrate saving and generates perceptually pleasant reconstructions compared to the state-of-the-art end-to-end image compression methods, which benefits the applications of focused plenoptic cameras greatly.
MLCopilot: Unleashing the Power of Large Language Models in Solving Machine Learning Tasks
In contrast, though human engineers have the incredible ability to understand tasks and reason about solutions, their experience and knowledge are often sparse and difficult to utilize by quantitative approaches.
Ranked #4 on
Code Generation
on DSEval-LeetCode
ElasticViT: Conflict-aware Supernet Training for Deploying Fast Vision Transformer on Diverse Mobile Devices
However, prior supernet training methods that rely on uniform sampling suffer from the gradient conflict issue: the sampled subnets can have vastly different model sizes (e. g., 50M vs. 2G FLOPs), leading to different optimization directions and inferior performance.
SpaceEvo: Hardware-Friendly Search Space Design for Efficient INT8 Inference
The combination of Neural Architecture Search (NAS) and quantization has proven successful in automatically designing low-FLOPs INT8 quantized neural networks (QNN).
Online Streaming Video Super-Resolution with Convolutional Look-Up Table
To facilitate the research on this problem, a new benchmark dataset named LDV-WebRTC is constructed based on a real-world online streaming system.
Unsupervised Video Anomaly Detection for Stereotypical Behaviours in Autism
Correspondingly, we propose a Dual Stream deep model for Stereotypical Behaviours Detection, DS-SBD, based on the temporal trajectory of human poses and the repetition patterns of human actions.
Towards Inference Efficient Deep Ensemble Learning
Ensemble methods can deliver surprising performance gains but also bring significantly higher computational costs, e. g., can be up to 2048X in large-scale ensemble tasks.
PIT: Optimization of Dynamic Sparse Deep Learning Models via Permutation Invariant Transformation
Dynamic sparsity, where the sparsity patterns are unknown until runtime, poses a significant challenge to deep learning.
Attentive Mask CLIP
To address this issue, we propose an attentive token removal approach for CLIP training, which retains tokens with a high semantic correlation to the text description.
DORE: Document Ordered Relation Extraction based on Generative Framework
In this paper, we investigate the root cause of the underwhelming performance of the existing generative DocRE models and discover that the culprit is the inadequacy of the training paradigm, instead of the capacities of the models.
Reinforcement Learning with Automated Auxiliary Loss Search
A good state representation is crucial to solving complicated reinforcement learning (RL) challenges.
Improving Hypernasality Estimation with Automatic Speech Recognition in Cleft Palate Speech
Specifically, we first pre-train an encoder-decoder framework in an automatic speech recognition (ASR) objective by using speech-to-text dataset, and then fine-tune ASR encoder on the cleft palate dataset for hypernasality estimation.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Online Video Super-Resolution with Convolutional Kernel Bypass Graft
Then, our proposed CKBG method enhances this lightweight base model by bypassing the original network with ``kernel grafts'', which are extra convolutional kernels containing the prior knowledge of external pretrained image SR models.
Privacy-preserving Online AutoML for Domain-Specific Face Detection
Thanks to HyperFD, each local task (client) is able to effectively leverage the learning "experience" of previous tasks without uploading raw images to the platform; meanwhile, the meta-feature extractor is continuously learned to better trade off the bias and variance.
Game of Privacy: Towards Better Federated Platform Collaboration under Privacy Restriction
To solve the game, we propose a platform negotiation method that simulates the bargaining among platforms and locally optimizes their policies via gradient descent.
Towards Generating Real-World Time Series Data
In this paper, we propose a novel generative framework for RTS data - RTSGAN to tackle the aforementioned challenges.
Variational oracle guiding for reinforcement learning
How to make intelligent decisions is a central problem in machine learning and cognitive science.
AARL: Automated Auxiliary Loss for Reinforcement Learning
A good state representation is crucial to reinforcement learning (RL) while an ideal representation is hard to learn only with signals from the RL objective.
Full-Cycle Energy Consumption Benchmark for Low-Carbon Computer Vision
The energy consumption of deep learning models is increasing at a breathtaking rate, which raises concerns due to potential negative effects on carbon neutrality in the context of global warming and climate change.
Learning to Rank Ace Neural Architectures via Normalized Discounted Cumulative Gain
One of the key challenges in Neural Architecture Search (NAS) is to efficiently rank the performances of architectures.
SPOC learner's final grade prediction based on a novel sampling batch normalization embedded neural network method
To solve this problem, a sampling batch normalization embedded deep neural network (SBNEDNN) method is developed in this paper.
Fast Hardware-Aware Neural Architecture Search
Unlike previous approaches that apply search algorithms on a small, human-designed search space without considering hardware diversity, we propose HURRICANE that explores the automatic hardware-aware search over a much larger search space and a two-stage search algorithm, to efficiently generate tailored models for different types of hardware.
