Search Results for author:
Found 46 papers, 21 papers with code
The Tenth NTIRE 2025 Image Denoising Challenge Report
This paper presents an overview of the NTIRE 2025 Image Denoising Challenge ({\sigma} = 50), highlighting the proposed methodologies and corresponding results.
Speculative End-Turn Detector for Efficient Speech Chatbot Assistant
Spoken dialogue systems powered by large language models have demonstrated remarkable abilities in understanding human speech and generating appropriate spoken responses.
Imagine to Hear: Auditory Knowledge Generation can be an Effective Assistant for Language Models
Language models pretrained on text-only corpora often struggle with tasks that require auditory commonsense knowledge.
On the Internal Representations of Graph Metanetworks
Weight space learning is an emerging paradigm in the deep learning community.
Prompt-based Depth Pruning of Large Language Models
Depth pruning aims to reduce the inference cost of a large language model without any hardware-specific complications, by simply removing several less important transformer blocks.
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
Fast Training of Sinusoidal Neural Fields via Scaling Initialization
Neural fields are an emerging paradigm that represent data as continuous functions parameterized by neural networks.
S2Cap: A Benchmark and a Baseline for Singing Style Captioning
However, existing open-source audio-text datasets for singing voices capture only a limited set of attributes and lacks acoustic features, leading to limited utility towards downstream tasks, such as style captioning.
AudioBERT: Audio Knowledge Augmented Language Model
Recent studies have identified that language models, pretrained on text-only datasets, often lack elementary visual knowledge, \textit{e. g.,} colors of everyday objects.
Decoding with Limited Teacher Supervision Requires Understanding When to Trust the Teacher
To this end, we develop an algorithm to effectively aggregate the small-scale LLM and LLM predictions on initial tokens so that the generated tokens can more accurately condition the subsequent token generation by small-scale LLM only.
Towards Federated Low-Rank Adaptation of Language Models with Rank Heterogeneity
Low-rank adaptation (LoRA) offers an efficient alternative to full-weight adaptation in federated fine-tuning of language models, significantly reducing computational costs.
Rethinking Pruning Large Language Models: Benefits and Pitfalls of Reconstruction Error Minimization
This work suggests fundamentally rethinking the current practice of pruning large language models (LLMs).
Prefixing Attention Sinks can Mitigate Activation Outliers for Large Language Model Quantization
Despite recent advances in LLM quantization, activation quantization remains to be challenging due to the activation outliers.
NTIRE 2024 Challenge on Low Light Image Enhancement: Methods and Results
This paper reviews the NTIRE 2024 low light image enhancement challenge, highlighting the proposed solutions and results.
Machine Learning-Assisted Thermoelectric Cooling for On-Demand Multi-Hotspot Thermal Management
Thermoelectric coolers (TECs) offer a promising solution for direct cooling of local hotspots and active thermal management in advanced electronic systems.
SCANNER: Knowledge-Enhanced Approach for Robust Multi-modal Named Entity Recognition of Unseen Entities
Our approach demonstrates competitive performance on the NER benchmark and surpasses existing methods on both MNER and GMNER benchmarks.
Multi-modal Named Entity Recognition
named-entity-recognition
+2
Neural Image Compression with Text-guided Encoding for both Pixel-level and Perceptual Fidelity
Recent advances in text-guided image compression have shown great potential to enhance the perceptual quality of reconstructed images.
Attention-aware Semantic Communications for Collaborative Inference
Therefore, instead of employing the partitioning strategy, our framework utilizes a lightweight ViT model on the edge device, with the server deploying a complicated ViT model.
Hybrid Neural Representations for Spherical Data
In this paper, we study hybrid neural representations for spherical data, a domain of increasing relevance in scientific research.
In Search of a Data Transformation That Accelerates Neural Field Training
Neural field is an emerging paradigm in data representation that trains a neural network to approximate the given signal.
Data-driven System Interconnections and a Novel Data-enabled Internal Model Control
Over the past two decades, there has been a growing interest in control systems research to transition from model-based methods to data-driven approaches.
Communication-Efficient Split Learning via Adaptive Feature-Wise Compression
In the second strategy, the non-dropped intermediate feature and gradient vectors are quantized using adaptive quantization levels determined based on the ranges of the vectors.
Debiased Distillation by Transplanting the Last Layer
Deep models are susceptible to learning spurious correlations, even during the post-processing.
The Role of Masking for Efficient Supervised Knowledge Distillation of Vision Transformers
Knowledge distillation is an effective method for training lightweight vision models.
Discovering and Mitigating Visual Biases through Keyword Explanation
The keyword explanation form of visual bias offers several advantages, such as a clear group naming for bias discovery and a natural extension for debiasing using these group names.
Modality-Agnostic Variational Compression of Implicit Neural Representations
We introduce a modality-agnostic neural compression algorithm based on a functional view of data and parameterised as an Implicit Neural Representation (INR).
Breaking the Spurious Causality of Conditional Generation via Fairness Intervention with Corrective Sampling
(a) Fairness Intervention (FI): emphasize the minority samples that are hard to generate due to the spurious correlation in the training dataset.
Data-Driven Inverse of Linear Systems and Application to Disturbance Observers
Specifically, the problem addressed here is to find an input sequence from the corresponding output sequence based on pre-collected input and output data.
Scalable Neural Video Representations with Learnable Positional Features
Succinct representation of complex signals using coordinate-based neural representations (CNRs) has seen great progress, and several recent efforts focus on extending them for handling videos.
Meta-Learning with Self-Improving Momentum Target
The idea of using a separately trained target model (or teacher) to improve the performance of the student model has been increasingly popular in various machine learning domains, and meta-learning is no exception; a recent discovery shows that utilizing task-wise target models can significantly boost the generalization performance.
Few-Shot Unlearning by Model Inversion
We consider a practical scenario of machine unlearning to erase a target dataset, which causes unexpected behavior from the trained model.
Zero-shot Blind Image Denoising via Implicit Neural Representations
Recent denoising algorithms based on the "blind-spot" strategy show impressive blind image denoising performances, without utilizing any external dataset.
Spread Spurious Attribute: Improving Worst-group Accuracy with Spurious Attribute Estimation
The paradigm of worst-group loss minimization has shown its promise in avoiding to learn spurious correlations, but requires costly additional supervision on spurious attributes.
Meta-Learning Sparse Implicit Neural Representations
Implicit neural representations are a promising new avenue of representing general signals by learning a continuous function that, parameterized as a neural network, maps the domain of a signal to its codomain; the mapping from spatial coordinates of an image to its pixel values, for example.
Co$^2$L: Contrastive Continual Learning
Recent breakthroughs in self-supervised learning show that such algorithms learn visual representations that can be transferred better to unseen tasks than joint-training methods relying on task-specific supervision.
Co2L: Contrastive Continual Learning
Recent breakthroughs in self-supervised learning show that such algorithms learn visual representations that can be transferred better to unseen tasks than cross-entropy based methods which rely on task-specific supervision.
MASKER: Masked Keyword Regularization for Reliable Text Classification
We claim that one central obstacle to the reliability is the over-reliance of the model on a limited number of keywords, instead of looking at the whole context.
Learning from Failure: De-biasing Classifier from Biased Classifier
Neural networks often learn to make predictions that overly rely on spurious corre- lation existing in the dataset, which causes the model to be biased.
Provable Memorization via Deep Neural Networks using Sub-linear Parameters
It is known that $O(N)$ parameters are sufficient for neural networks to memorize arbitrary $N$ input-label pairs.
Layer-adaptive sparsity for the Magnitude-based Pruning
Recent discoveries on neural network pruning reveal that, with a carefully chosen layerwise sparsity, a simple magnitude-based pruning achieves state-of-the-art tradeoff between sparsity and performance.
Learning from Failure: Training Debiased Classifier from Biased Classifier
Neural networks often learn to make predictions that overly rely on spurious correlation existing in the dataset, which causes the model to be biased.
Ranked #1 on
Out-of-Distribution Generalization
on ImageNet-W
Minimum Width for Universal Approximation
In this work, we provide the first definitive result in this direction for networks using the ReLU activation functions: The minimum width required for the universal approximation of the $L^p$ functions is exactly $\max\{d_x+1, d_y\}$.
Learning Bounds for Risk-sensitive Learning
The second result, based on a novel variance-based characterization of OCE, gives an expected loss guarantee with a suppressed dependence on the smoothness of the selected OCE.
Lookahead: a Far-Sighted Alternative of Magnitude-based Pruning
Magnitude-based pruning is one of the simplest methods for pruning neural networks.
Learning finite-dimensional coding schemes with nonlinear reconstruction maps
This paper generalizes the Maurer--Pontil framework of finite-dimensional lossy coding schemes to the setting where a high-dimensional random vector is mapped to an element of a compact set of latent representations in a lower-dimensional Euclidean space, and the reconstruction map belongs to a given class of nonlinear maps.
Minimax Statistical Learning with Wasserstein Distances
As opposed to standard empirical risk minimization (ERM), distributionally robust optimization aims to minimize the worst-case risk over a larger ambiguity set containing the original empirical distribution of the training data.
