Search Results for author:
Found 20 papers, 9 papers with code
Can LLMs Maintain Fundamental Abilities under KV Cache Compression?
We present a comprehensive empirical study evaluating prominent KV cache compression methods across diverse tasks, spanning world knowledge, commonsense reasoning, arithmetic reasoning, code generation, safety, and long-context understanding and generation. Our analysis reveals that KV cache compression methods exhibit task-specific performance degradation.
ChunkKV: Semantic-Preserving KV Cache Compression for Efficient Long-Context LLM Inference
To reduce memory costs in long-context inference with Large Language Models (LLMs), many recent works focus on compressing the key-value (KV) cache of different tokens.
Representational Transfer Learning for Matrix Completion
We propose to transfer representational knowledge from multiple sources to a target noisy matrix completion task by aggregating singular subspaces information.
AI-generated Image Detection: Passive or Watermark?
Based on these insights, we provide recommendations for detecting AI-generated images, e. g., when both types of detectors are applicable, watermark-based detectors should be the preferred choice.
Should We Really Edit Language Models? On the Evaluation of Edited Language Models
Our findings indicate that current editing methods are only suitable for small-scale knowledge updates within language models, which motivates further research on more practical and reliable editing methods.
OpenAnimals: Revisiting Person Re-Identification for Animals Towards Better Generalization
This paper addresses the challenge of animal re-identification, an emerging field that shares similarities with person re-identification but presents unique complexities due to the diverse species, environments and poses.
Physics-aligned Schrödinger bridge
To overcome this limitation, we introduce a novel data-driven field reconstruction framework, termed the Physics-aligned Schr\"{o}dinger Bridge (PalSB).
MaterialSeg3D: Segmenting Dense Materials from 2D Priors for 3D Assets
Driven by powerful image diffusion models, recent research has achieved the automatic creation of 3D objects from textual or visual guidance.
Knowledge Transfer across Multiple Principal Component Analysis Studies
In the first step, we integrate the shared subspace information across multiple studies by a proposed method named as Grassmannian barycenter, instead of directly performing PCA on the pooled dataset.
Oceanship: A Large-Scale Dataset for Underwater Audio Target Recognition
While audio retrieval tasks are well-established in general audio classification, they have not been explored in the context of underwater audio recognition.
MEAOD: Model Extraction Attack against Object Detectors
The widespread use of deep learning technology across various industries has made deep neural network models highly valuable and, as a result, attractive targets for potential attackers.
Geo2SigMap: High-Fidelity RF Signal Mapping Using Geographic Databases
First, we develop an automated framework that seamlessly integrates three open-source tools: OpenStreetMap (geographic databases), Blender (computer graphics), and Sionna (ray tracing), enabling the efficient generation of large-scale 3D building maps and ray tracing models.
Dissecting the Runtime Performance of the Training, Fine-tuning, and Inference of Large Language Models
For end users, our benchmark and findings help better understand different optimization techniques, training and inference frameworks, together with hardware platforms in choosing configurations for deploying LLMs.
CluCDD:Contrastive Dialogue Disentanglement via Clustering
A huge number of multi-participant dialogues happen online every day, which leads to difficulty in understanding the nature of dialogue dynamics for both humans and machines.
Powering Comparative Classification with Sentiment Analysis via Domain Adaptive Knowledge Transfer
We study Comparative Preference Classification (CPC) which aims at predicting whether a preference comparison exists between two entities in a given sentence and, if so, which entity is preferred over the other.
Recommend for a Reason: Unlocking the Power of Unsupervised Aspect-Sentiment Co-Extraction
Compliments and concerns in reviews are valuable for understanding users' shopping interests and their opinions with respect to specific aspects of certain items.
Towards Visual Explainable Active Learning for Zero-Shot Classification
This paper proposes a visual explainable active learning approach with its design and implementation called semantic navigator to solve the above problems.
Interpretable Click-Through Rate Prediction through Hierarchical Attention
For this problem, existing approaches, with shallow or deep architectures, have three major drawbacks.
Learning Gender-Neutral Word Embeddings
Word embedding models have become a fundamental component in a wide range of Natural Language Processing (NLP) applications.
Peeking the Impact of Points of Interests on Didi
Recently, the online car-hailing service, Didi, has emerged as a leader in the sharing economy.
