32 accepted papers
Large language models (LLMs) have achieved remarkable success, but their rapidly growing scale imposes prohibitive costs in memory, computation, and energy. Post-training quantization (PTQ) is a promising solution for efficient deployment, yet achieving accurate W4A4 quantization remains an open cha…
Test-time scaling improves LLM performance by generating multiple candidate solutions, yet token-level sampling requires temperature tuning that trades off diversity against stability. Fine-grained MoE, featuring hundreds of well-trained experts per layer and multi-expert activation per token, offer…
Recent years have witnessed growing scholarly interest in binary post-training quantization (PTQ) techniques for large language models (LLMs). While state-of-the-art (SOTA) binary quantization methods significantly reduce memory footprint and computational demands, they introduce additional memory o
Large language models (LLMs) excel at logical and algorithmic reasoning, yet their emotional intelligence (EQ) still lags far behind their cognitive prowess. While reinforcement learning from verifiable rewards (RLVR) has advanced in other domains, its application to dialogue—especially for emotion…
Visual AutoRegressive (VAR) modeling has garnered significant attention for its innovative next-scale prediction paradigm. However, mainstream VAR paradigms attend to all tokens across historical scales at each autoregressive step. As the next scale resolution grows, the computational complexity of
Cross-domain offline reinforcement learning (RL) aims to train an agent that performs well in the target domain using a limited target domain dataset and a source domain dataset that exhibits a dynamics shift. Training directly on the original source dataset typically leads to performance collapse. …
Quantization plays a crucial role in accelerating the inference of large-scale models, and rotational matrices have been shown to effectively improve quantization performance by smoothing outliers. However, end-to-end fine-tuning of rotational optimization algorithms incurs high computational costs…
Mixture-of-Experts (MoE) has demonstrated promising potential in scaling LLMs. However, it is hindered by two critical challenges: (1) substantial GPU memory consumption to load all experts; (2) low activated parameters cannot be equivalently translated into inference acceleration effects. In this w…
Though Rectified Flows (ReFlows) with distillation offer a promising way for fast sampling, its fast inversion transforms images back to structured noise for recovery and following editing remains unsolved. This paper introduces FireFlow, an embarrassingly simple yet effective zero-shot approach tha…
As the parameter size of language models becomes extremely large, fine-tuning them with limited resources has become a challenging task. Latest advancements in parameter-efficient fine-tuning (PEFT) techniques allow for adjustments to only a minor fraction of the parameters of these LLMs. Yet, most
State Space Models (SSMs), such as Mamba, have recently demonstrated potential in language understanding tasks, positioning them as competitors to transformer architectures. However, our investigations reveal that the Mamba architecture still has room for further optimization—not only in linear proj…
Delta compression methods focus on efficiently serving multiple uniquely fine-tuned models, each tailored to specific tasks and user requirements. These approaches decompose a fine-tuned LLM into a base model and corresponding delta weights, which are compressed using low-rank or low-bit representat…
Recent studies have demonstrated the effectiveness of LLM test-time scaling. However, existing approaches to incentivize LLMs’ deep thinking abilities generally require large-scale data or significant training efforts. Meanwhile, it remains unclear how to improve the thinking abilities of less power…
Evaluating the step-by-step reliability of large language model (LLM) reasoning, such as Chain-of-Thought, remains challenging due to the difficulty and cost of obtaining high-quality step-level supervision. In this paper, we introduce Self-Play Critic (SPC), a novel approach where a critic model ev…
Graph plays a significant role in representing and analyzing complex relationships in real-world applications such as citation networks, social networks, and biological data. Recently, Large Language Models (LLMs), which have achieved tremendous success in various domains, have also been leveraged i…
The emergence of large language models (LLMs) has revolutionized the way we interact with graphs, leading to a new paradigm called GraphLLM. Despite the rapid development of GraphLLM methods in recent years, the progress and understanding of this field remain unclear due to the lack of a benchmark w…
Nowadays sample selection is drawing increasing attention. By extracting and training only on the most informative subset, sample selection can effectively reduce the training cost. Although sample selection is effective in conventional supervised learning, applying it to Masked Image Modeling (MIM)…
Nowadays Spiking Transformers have exhibited remarkable performance close to Artificial Neural Networks (ANNs), while enjoying the inherent energy-efficiency of Spiking Neural Networks (SNNs). However, training Spiking Transformers on GPUs is considerably more time-consuming compared to the ANN coun…
The Winograd algorithm is an efficient convolution implementation, which performs calculations in the transformed domain. To further improve the computation efficiency, recent works propose to combine it with model quantization. Although Post-Training Quantization has the advantage of low computatio…
Training deep neural networks (DNNs) for meaningful differential privacy (DP) guarantees severely degrades model utility. In this paper, we demonstrate that the architecture of DNNs has a significant impact on model utility in the context of private deep learning, whereas its effect is largely unexp…
User-level differential privacy (DP) provides certifiable privacy guarantees to the information that is specific to any user's data in federated learning. Existing methods that ensure user-level DP come at the cost of severe accuracy decrease. In this paper, we study the cause of model performance d…
The 2:4 structured sparsity pattern released by NVIDIA Ampere architecture, requiring four consecutive values containing at least two zeros, enables doubling math throughput for matrix multiplications. Recent works mainly focus on inference speedup via 2:4 sparsity while training acceleration has be…
Electrostatic film actuators are an emerging flexible actuation technique based on the electrostatic field. It is typically composed of two films (the stator and the slider), each of which integrates multiple phase interdigital electrodes. Since the structure and the electrical field distribution ar
Quantization is a widely used technique to compress and accelerate deep neural networks. However, conventional quantization methods use the same bit-width for all (or most of) the layers, which often suffer significant accuracy degradation in the ultra-low precision regime and ignore the fact that e…
Training Binarized Neural Networks (BNNs) is challenging due to the discreteness. In order to efficiently optimize BNNs through backward propagations, real-valued auxiliary variables are commonly used to accumulate gradient updates. Those auxiliary variables are then directly quantized to binary wei…
Large neural networks are difficult to deploy on mobile devices because of intensive computation and storage. To alleviate it, we study ternarization, a balance between efficiency and accuracy that quantizes both weights and activations into ternary values. In previous ternarized neural networks, a…
Network quantization is essential for deploying deep models to IoT devices due to its high efficiency. Most existing quantization approaches rely on the full training datasets and the time-consuming fine-tuning to retain accuracy. Post-training quantization does not have these problems, however, it…
Hashing based approximate nearest neighbor search embeds high dimensional data to compact binary codes, which enables efficient similarity search and storage. However, the non-isometry sign() function makes it hard to project the nearest neighbors in continuous data space into the closest codewords…
Single image super-resolution, as a high dimensional structured prediction problem, aims to characterize fine-grain information given a low-resolution sample. Recent advances in convolutional neural networks are introduced into super-resolution and push forward progress in this field. Current studie…
Recently binary weight networks have attracted lots of attentions due to their high computational efficiency and small parameter size. Yet they still suffer from large accuracy drops because of their limited representation capacity. In this paper, we propose a novel semi-binary decomposition method…
Every bit matters in the hardware design of quantized neural networks. However, extremely-low-bit representation usually causes large accuracy drop. Thus, how to train extremely-low-bit neural networks with high accuracy is of central importance. Most existing network quantization approaches learn t…
In recent years, Deep Neural Networks (DNN) based methods have achieved remarkable performance in a wide range of tasks and have been among the most powerful and widely used techniques in computer vision. However, DNN-based methods are both computational-intensive and resource-consuming, which hinde…