Search Results for author:
Found 42 papers, 12 papers with code
SecurityLingua: Efficient Defense of LLM Jailbreak Attacks via Security-Aware Prompt Compression
In this paper, we propose SecurityLingua, an effective and efficient approach to defend LLMs against jailbreak attacks via security-oriented prompt compression.
ReasonGen-R1: CoT for Autoregressive Image generation models through SFT and RL
Although chain-of-thought reasoning and reinforcement learning (RL) have driven breakthroughs in NLP, their integration into generative vision models remains underexplored.
Chain-of-Model Learning for Language Model
In this paper, we propose a novel learning paradigm, termed Chain-of-Model (CoM), which incorporates the causal relationship into the hidden states of each layer as a chain style, thereby introducing great scaling efficiency in model training and inference flexibility in deployment.
Empowering Agentic Video Analytics Systems with Video Language Models
Furthermore, to evaluate video analytics in ultra-long and open-world video scenarios, we introduce a new benchmark, AVAS-100.
Zoomer: Adaptive Image Focus Optimization for Black-box MLLM
Recent advancements in multimodal large language models (MLLMs) have broadened the scope of vision-language tasks, excelling in applications like image captioning and interactive question-answering.
MMInference: Accelerating Pre-filling for Long-Context VLMs via Modality-Aware Permutation Sparse Attention
We introduce a permutation-based method to leverage the unique Grid pattern and handle modality boundary issues.
Advancing Mobile GUI Agents: A Verifier-Driven Approach to Practical Deployment
We propose V-Droid, a mobile GUI task automation agent.
HiTVideo: Hierarchical Tokenizers for Enhancing Text-to-Video Generation with Autoregressive Large Language Models
We explore the trade-offs between compression and reconstruction, while emphasizing the advantages of high-compressed semantic tokens in text-to-video tasks.
VoLUT: Efficient Volumetric streaming enhanced by LUT-based super-resolution
A natural approach to mitigate the bandwidth issue is to reduce the volumetric video's data rate by downsampling the content prior to transmission.
On Memory Construction and Retrieval for Personalized Conversational Agents
To deliver coherent and personalized experiences in long-term conversations, existing approaches typically perform retrieval augmented response generation by constructing memory banks from conversation history at either the turn-level, session-level, or through summarization techniques. In this paper, we present two key findings: (1) The granularity of memory unit matters: turn-level, session-level, and summarization-based methods each exhibit limitations in both memory retrieval accuracy and the semantic quality of the retrieved content.
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 representation space via 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.
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.
Babel: A Scalable Pre-trained Model for Multi-Modal Sensing via Expandable Modality Alignment
This paper presents Babel, the expandable modality alignment model, specially designed for multi-modal sensing.
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.
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).
LLM-RadJudge: Achieving Radiologist-Level Evaluation for X-Ray Report Generation
This study proposes a novel evaluation framework using large language models (LLMs) to compare radiology reports for assessment.
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.
EEGFormer: Towards Transferable and Interpretable Large-Scale EEG Foundation Model
Self-supervised learning has emerged as a highly effective approach in the fields of natural language processing and computer vision.
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).
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.
Empowering In-Browser Deep Learning Inference on Edge Devices with Just-in-Time Kernel Optimizations
Web is increasingly becoming the primary platform to deliver AI services onto edge devices, making in-browser deep learning (DL) inference more prominent.
Seeing through the Brain: Image Reconstruction of Visual Perception from Human Brain Signals
Seeing is believing, however, the underlying mechanism of how human visual perceptions are intertwined with our cognitions is still a mystery.
Real-Time Neural Video Recovery and Enhancement on Mobile Devices
Although deep learning-based video enhancement techniques are gaining attention, most of them cannot support real-time enhancement on mobile devices.
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.
Protecting the Future: Neonatal Seizure Detection with Spatial-Temporal Modeling
A timely detection of seizures for newborn infants with electroencephalogram (EEG) has been a common yet life-saving practice in the Neonatal Intensive Care Unit (NICU).
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
Adaptive Scheduling for Edge-Assisted DNN Serving
Based on this observation, we first design a novel scheduling algorithm to exploit the batching benefits of all requests that run the same DNN.
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.
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.
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)
+3
CMMD: Cross-Metric Multi-Dimensional Root Cause Analysis
To this end, we propose a cross-metric multi-dimensional root cause analysis method, named CMMD, which consists of two key components: 1) relationship modeling, which utilizes graph neural network (GNN) to model the unknown complex calculation among metrics and aggregation function among dimensions from historical data; 2) root cause localization, which adopts the genetic algorithm to efficiently and effectively dive into the raw data and localize the abnormal dimension(s) once the KPI anomalies are detected.
