Search Results for author:
Found 68 papers, 47 papers with code
Double-Checker: Enhancing Reasoning of Slow-Thinking LLMs via Self-Critical Fine-Tuning
While slow-thinking large language models (LLMs) exhibit reflection-like reasoning, commonly referred to as the "aha moment:, their ability to generate informative critiques and refine prior solutions remains limited.
GPTailor: Large Language Model Pruning Through Layer Cutting and Stitching
Large language models (LLMs) have shown remarkable capabilities in language understanding and generation.
AlphaDecay: Module-wise Weight Decay for Heavy-Tailed Balancing in LLMs
While it is common to assign a uniform decay rate to every layer, this approach overlooks the structural diversity of LLMs and the varying spectral properties across modules.
A Technical Study into Small Reasoning Language Models
The ongoing evolution of language models has led to the development of large-scale architectures that demonstrate exceptional performance across a wide range of tasks.
Leave it to the Specialist: Repair Sparse LLMs with Sparse Fine-Tuning via Sparsity Evolution
Large language models (LLMs) have achieved remarkable success across various tasks but face deployment challenges due to their massive computational demands.
Stable-SPAM: How to Train in 4-Bit More Stably than 16-Bit Adam
This paper comprehensively evaluates several recently proposed optimizers for 4-bit training, revealing that low-bit precision amplifies sensitivity to learning rates and often causes unstable gradient norms, leading to divergence at higher learning rates.
Mask-Enhanced Autoregressive Prediction: Pay Less Attention to Learn More
To address this, we propose Mask-Enhanced Autoregressive Prediction (MEAP), a simple yet effective training paradigm that seamlessly integrates Masked Language Modeling (MLM) into Next-Token Prediction (NTP) to enhance the latter's in-context retrieval capabilities.
The Curse of Depth in Large Language Models
While Pre-LN stabilizes the training of Transformer LLMs, its output variance exponentially grows with the model depth, which undesirably causes the derivative of the deep Transformer blocks to be an identity matrix, and therefore barely contributes to the training.
O1-Pruner: Length-Harmonizing Fine-Tuning for O1-Like Reasoning Pruning
Experiments on various mathematical reasoning benchmarks show that O1-Pruner not only significantly reduces inference overhead but also achieves higher accuracy, providing a novel and promising solution to this challenge.
SPAM: Spike-Aware Adam with Momentum Reset for Stable LLM Training
Large Language Models (LLMs) have demonstrated exceptional performance across diverse tasks, yet their training remains highly resource-intensive and susceptible to critical challenges such as training instability.
Mix-LN: Unleashing the Power of Deeper Layers by Combining Pre-LN and Post-LN
In contrast, Post-Layer Normalization (Post-LN) preserves larger gradient norms in deeper layers but suffers from vanishing gradients in earlier layers.
SIDE: Socially Informed Drought Estimation Toward Understanding Societal Impact Dynamics of Environmental Crisis
Drought has become a critical global threat with significant societal impact.
Condense, Don't Just Prune: Enhancing Efficiency and Performance in MoE Layer Pruning
Mixture-of-Experts (MOE) has garnered significant attention for their ability to scale up neural networks while utilizing the same or even fewer active parameters.
AlphaPruning: Using Heavy-Tailed Self Regularization Theory for Improved Layer-wise Pruning of Large Language Models
Existing LLM pruning strategies typically assign uniform pruning ratios across layers, limiting overall pruning ability; and recent work on layerwise pruning of LLMs is often based on heuristics that can easily lead to suboptimal performance.
Full-Rank No More: Low-Rank Weight Training for Modern Speech Recognition Models
This paper investigates the under-explored area of low-rank weight training for large-scale Conformer-based speech recognition models from scratch.
Is C4 Dataset Optimal for Pruning? An Investigation of Calibration Data for LLM Pruning
In this study, we evaluate the choice of calibration data on LLM pruning, across a wide range of datasets that are most commonly used in LLM training and evaluation, including four pertaining datasets as well as three categories of downstream tasks encompassing nine datasets.
(PASS) Visual Prompt Locates Good Structure Sparsity through a Recurrent HyperNetwork
In this paper, we investigate a charming possibility - \textit{leveraging visual prompts to capture the channel importance and derive high-quality structural sparsity}.
From GaLore to WeLore: How Low-Rank Weights Non-uniformly Emerge from Low-Rank Gradients
Modern Large Language Models (LLMs) are composed of matrices with billions of elements, making their storage and processing quite demanding in terms of computational resources and memory usage.
Q-GaLore: Quantized GaLore with INT4 Projection and Layer-Adaptive Low-Rank Gradients
To address these limitations, we introduce Q-Galore, a novel approach that substantially reduces memory usage by combining quantization and low-rank projection, surpassing the benefits of GaLore.
Composable Interventions for Language Models
Test-time interventions for language models can enhance factual accuracy, mitigate harmful outputs, and improve model efficiency without costly retraining.
Multi-branch CNN and grouping cascade attention for medical image classification
In addition, we propose an efficient CNN (EC) module to enhance the ability of the model and extract the local detail information in medical images.
Dynamic Data Pruning for Automatic Speech Recognition
The recent success of Automatic Speech Recognition (ASR) is largely attributed to the ever-growing amount of training data.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
MSRS: Training Multimodal Speech Recognition Models from Scratch with Sparse Mask Optimization
In this study, we propose a regularization technique that facilitates the training of visual and audio-visual speech recognition models (VSR and AVSR) from scratch.
Towards Efficient Pareto Set Approximation via Mixture of Experts Based Model Fusion
Once the routers are learned and a preference vector is set, the MoE module can be unloaded, thus no additional computational cost is introduced during inference.
OwLore: Outlier-weighed Layerwise Sampled Low-Rank Projection for Memory-Efficient LLM Fine-tuning
The rapid advancements in Large Language Models (LLMs) have revolutionized various natural language processing tasks.
FFN-SkipLLM: A Hidden Gem for Autoregressive Decoding with Adaptive Feed Forward Skipping
In this work, we observed the saturation of computationally expensive feed-forward blocks of LLM layers and proposed FFN-SkipLLM, which is a novel fine-grained skip strategy of autoregressive LLMs.
Found in the Middle: How Language Models Use Long Contexts Better via Plug-and-Play Positional Encoding
To address this problem, this paper introduces Multi-scale Positional Encoding (Ms-PoE) which is a simple yet effective plug-and-play approach to enhance the capacity of LLMs to handle the relevant information located in the middle of the context, without fine-tuning or introducing any additional overhead.
ConSmax: Hardware-Friendly Alternative Softmax with Learnable Parameters
Experimental results show that ConSmax achieves a minuscule power consumption of 0. 2mW and an area of 0. 0008mm^2 at 1250MHz working frequency in 16nm FinFET technology.
The Counterattack of CNNs in Self-Supervised Learning: Larger Kernel Size might be All You Need
Therefore, it remains unclear whether the self-attention operation is crucial for the recent advances in SSL - or CNNs can deliver the same excellence with more advanced designs, too?
E2ENet: Dynamic Sparse Feature Fusion for Accurate and Efficient 3D Medical Image Segmentation
E2ENet achieves comparable accuracy on the large-scale challenge AMOS-CT, while saving over 68\% parameter count and 29\% FLOPs in the inference phase, compared with the previous best-performing method.
REST: Enhancing Group Robustness in DNNs through Reweighted Sparse Training
These bias attributes are strongly spuriously correlated with the target variable, causing the models to be biased towards spurious correlations (i. e., \textit{bias-conflicting}).
Visual Prompting Upgrades Neural Network Sparsification: A Data-Model Perspective
The rapid development of large-scale deep learning models questions the affordability of hardware platforms, which necessitates the pruning to reduce their computational and memory footprints.
Predicting mutational effects on protein-protein binding via a side-chain diffusion probabilistic model
Many crucial biological processes rely on networks of protein-protein interactions.
Dynamic Sparse No Training: Training-Free Fine-tuning for Sparse LLMs
Inspired by the Dynamic Sparse Training, DSnoT minimizes the reconstruction error between the dense and sparse LLMs, in the fashion of performing iterative weight pruning-and-growing on top of sparse LLMs.
Outlier Weighed Layerwise Sparsity (OWL): A Missing Secret Sauce for Pruning LLMs to High Sparsity
Large Language Models (LLMs), renowned for their remarkable performance across diverse domains, present a challenge when it comes to practical deployment due to their colossal model size.
AdaMerging: Adaptive Model Merging for Multi-Task Learning
This approach aims to autonomously learn the coefficients for model merging, either in a task-wise or layer-wise manner, without relying on the original training data.
Pruning Small Pre-Trained Weights Irreversibly and Monotonically Impairs "Difficult" Downstream Tasks in LLMs
Contrary to this belief, this paper presents a counter-argument: small-magnitude weights of pre-trained model weights encode vital knowledge essential for tackling difficult downstream tasks - manifested as the monotonic relationship between the performance drop of downstream tasks across the difficulty spectrum, as we prune more pre-trained weights by magnitude.
Enhancing Adversarial Training via Reweighting Optimization Trajectory
Despite the fact that adversarial training has become the de facto method for improving the robustness of deep neural networks, it is well-known that vanilla adversarial training suffers from daunting robust overfitting, resulting in unsatisfactory robust generalization.
Instant Soup: Cheap Pruning Ensembles in A Single Pass Can Draw Lottery Tickets from Large Models
Motivated by the recent observations of model soups, which suggest that fine-tuned weights of multiple models can be merged to a better minima, we propose Instant Soup Pruning (ISP) to generate lottery ticket quality subnetworks, using a fraction of the original IMP cost by replacing the expensive intermediate pruning stages of IMP with computationally efficient weak mask generation and aggregation routine.
Graph Ladling: Shockingly Simple Parallel GNN Training without Intermediate Communication
By dividing giant graph data, we build multiple independently and parallelly trained weaker GNNs (soup ingredient) without any intermediate communication, and combine their strength using a greedy interpolation soup procedure to achieve state-of-the-art performance.
The Emergence of Essential Sparsity in Large Pre-trained Models: The Weights that Matter
Large pre-trained transformers are show-stealer in modern-day deep learning, and it becomes crucial to comprehend the parsimonious patterns that exist within them as they grow in scale.
Are Large Kernels Better Teachers than Transformers for ConvNets?
We hereby carry out a first-of-its-kind study unveiling that modern large-kernel ConvNets, a compelling competitor to Vision Transformers, are remarkably more effective teachers for small-kernel ConvNets, due to more similar architectures.
Supervised Feature Selection with Neuron Evolution in Sparse Neural Networks
Feature selection that selects an informative subset of variables from data not only enhances the model interpretability and performance but also alleviates the resource demands.
Sparsity May Cry: Let Us Fail (Current) Sparse Neural Networks Together!
In pursuit of a more general evaluation and unveiling the true potential of sparse algorithms, we introduce "Sparsity May Cry" Benchmark (SMC-Bench), a collection of carefully-curated 4 diverse tasks with 10 datasets, that accounts for capturing a wide range of domain-specific and sophisticated knowledge.
Sparse MoE as the New Dropout: Scaling Dense and Self-Slimmable Transformers
Despite their remarkable achievement, gigantic transformers encounter significant drawbacks, including exorbitant computational and memory footprints during training, as well as severe collapse evidenced by a high degree of parameter redundancy.
Ten Lessons We Have Learned in the New "Sparseland": A Short Handbook for Sparse Neural Network Researchers
In response, we summarize ten Q\&As of SNNs from many key aspects, including dense vs. sparse, unstructured sparse vs. structured sparse, pruning vs. sparse training, dense-to-sparse training vs. sparse-to-sparse training, static sparsity vs. dynamic sparsity, before-training/during-training vs. post-training sparsity, and many more.
Data Augmented Flatness-aware Gradient Projection for Continual Learning
In this paper, we first revisit the gradient projection method from the perspective of flatness of loss surface, and find that unflatness of the loss surface leads to catastrophic forgetting of the old tasks when the projection constraint is reduced to improve the performance of new tasks.
Dynamic Sparse Network for Time Series Classification: Learning What to "see''
The receptive field (RF), which determines the region of time series to be ``seen'' and used, is critical to improve the performance for time series classification (TSC).
You Can Have Better Graph Neural Networks by Not Training Weights at All: Finding Untrained GNNs Tickets
Recent works have impressively demonstrated that there exists a subnetwork in randomly initialized convolutional neural networks (CNNs) that can match the performance of the fully trained dense networks at initialization, without any optimization of the weights of the network (i. e., untrained networks).
Lottery Pools: Winning More by Interpolating Tickets without Increasing Training or Inference Cost
We call our method Lottery Pools.
More ConvNets in the 2020s: Scaling up Kernels Beyond 51x51 using Sparsity
Transformers have quickly shined in the computer vision world since the emergence of Vision Transformers (ViTs).
Superposing Many Tickets into One: A Performance Booster for Sparse Neural Network Training
Recent works on sparse neural network training (sparse training) have shown that a compelling trade-off between performance and efficiency can be achieved by training intrinsically sparse neural networks from scratch.
Don't Be So Dense: Sparse-to-Sparse GAN Training Without Sacrificing Performance
Even more unconventionally, our proposed method enables directly training sparse unbalanced GANs with an extremely sparse generator from scratch.
The Unreasonable Effectiveness of Random Pruning: Return of the Most Naive Baseline for Sparse Training
In this paper, we focus on sparse training and highlight a perhaps counter-intuitive finding, that random pruning at initialization can be quite powerful for the sparse training of modern neural networks.
Achieving Personalized Federated Learning with Sparse Local Models
To counter this issue, personalized FL (PFL) was proposed to produce dedicated local models for each individual user.
Sparse Unbalanced GAN Training with In-Time Over-Parameterization
Perhaps most importantly, we find instead of inheriting parameters from expensive pre-trained GANs, directly training sparse GANs from scratch can be a much more efficient solution.
On Heterogeneously Distributed Data, Sparsity Matters
Federated learning (FL) is particularly vulnerable to heterogeneously distributed data, since a common global model in FL may not adapt to the heterogeneous data distribution of each user.
Hierarchical Semantic Segmentation using Psychometric Learning
One of the major challenges in the supervised learning approaches is expressing and collecting the rich knowledge that experts have with respect to the meaning present in the image data.
Deep Ensembling with No Overhead for either Training or Testing: The All-Round Blessings of Dynamic Sparsity
Our framework, FreeTickets, is defined as the ensemble of these relatively cheap sparse subnetworks.
Sparse Training via Boosting Pruning Plasticity with Neuroregeneration
Works on lottery ticket hypothesis (LTH) and single-shot network pruning (SNIP) have raised a lot of attention currently on post-training pruning (iterative magnitude pruning), and before-training pruning (pruning at initialization).
Ranked #3 on
Sparse Learning
on ImageNet
Do We Actually Need Dense Over-Parameterization? In-Time Over-Parameterization in Sparse Training
By starting from a random sparse network and continuously exploring sparse connectivities during training, we can perform an Over-Parameterization in the space-time manifold, closing the gap in the expressibility between sparse training and dense training.
Ranked #4 on
Sparse Learning
on ImageNet
Mitigating the effect of atmospheric turbulence on orbital angular momentum-based quantum key distribution using real-time adaptive optics with phase unwrapping
Quantum key distribution (QKD) employed orbital angular momentum (OAM) for high-dimensional encoding enhances the system security and information capacity between two communication parties.
Quantum Physics
Selfish Sparse RNN Training
Sparse neural networks have been widely applied to reduce the computational demands of training and deploying over-parameterized deep neural networks.
Topological Insights into Sparse Neural Networks
However, comparing different sparse topologies and determining how sparse topologies evolve during training, especially for the situation in which the sparse structure optimization is involved, remain as challenging open questions.
On improving deep learning generalization with adaptive sparse connectivity
Large neural networks are very successful in various tasks.
A Brain-inspired Algorithm for Training Highly Sparse Neural Networks
Concretely, by exploiting the cosine similarity metric to measure the importance of the connections, our proposed method, Cosine similarity-based and Random Topology Exploration (CTRE), evolves the topology of sparse neural networks by adding the most important connections to the network without calculating dense gradient in the backward.
Sparse evolutionary Deep Learning with over one million artificial neurons on commodity hardware
Despite the success of ANNs, it is challenging to train and deploy modern ANNs on commodity hardware due to the ever-increasing model size and the unprecedented growth in the data volumes.
Intrinsically Sparse Long Short-Term Memory Networks
However, LSTMs are prone to be memory-bandwidth limited in realistic applications and need an unbearable period of training and inference time as the model size is ever-increasing.
