Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileAcademic lineage
Possible advisorsa guess from early papers, not confirmed
- Xianglong LiuSuggested from co-authorship
Is this you? Claim this profile to confirm or dismiss it.
Works73 from public data
- Binary neural networks: A survey597
A comprehensive survey of algorithms proposed for binary neural networks, mainly categorized into the native solutions directly conducting binarization, and the optimized ones using techniques like minimizing the quantization error, improving the network loss function, and reducing the gradient error are presented.
- Differentiable Soft Quantization: Bridging Full-Precision and Low-Bit Neural Networks563
Differentiable Soft Quantization (DSQ) is proposed to bridge the gap between the full-precision and low-bit networks and can help pursue the accurate gradients in backward propagation, and reduce the quantization loss in forward process with an appropriate clipping range.
- Forward and Backward Information Retention for Accurate Binary Neural Networks412
The proposed Information Retention Network (IR-Net) is the first to investigate both forward and backward processes of binary networks from the unified information perspective, which provides new insight into the mechanism of network binarization.
- QDrop: Randomly Dropping Quantization for Extremely Low-bit Post-Training Quantization295
It is pioneeringly confirmed that properly incorporating activation quantization into the PTQ reconstruction benefits the final accuracy, and a simple yet effective approach dubbed as QDROP is proposed, which randomly drops the quantization of activations during PTQ.
- Towards Unified INT8 Training for Convolutional Neural Network185
An attempt to build a unified 8-bit (INT8) training framework for common convolutional neural networks from the aspects of both accuracy and speed is given and two universal techniques are proposed that reduce the direction deviation of gradients and avoid illegal gradient update along the wrong direction.
- Distribution-Sensitive Information Retention for Accurate Binary Neural Network156
A novel distribution-sensitive information retention network (DIR-Net) that retains the information in the forward and backward propagation by improving internal propagation and introducing external representations and consistently outperforms the state-of-the-art binarization approaches under mainstream and compact architectures.
- Diversifying Sample Generation for Accurate Data-Free Quantization118
This work proposes Diverse Sample Generation (DSG) scheme, which slack the alignment of feature statistics in the BN layer to relax the constraint at the distribution level and design a layerwise enhancement to reinforce specific layers for different data samples.
- Outlier Suppression+: Accurate quantization of large language models by equivalent and effective shifting and scaling97
The Outlier Suppression+~(OS+) framework, which contains the channel-wise shifting for asymmetry and channel- wise scaling for concentration, can be seamlessly migrated into subsequent modules while maintaining equivalence and validated under both standard and fine-grained quantization settings.
- QLLM: Accurate and Efficient Low-Bitwidth Quantization for Large Language Models89
QLLM is proposed, an accurate and efficient low-bitwidth PTQ method designed for LLMs that introduces an adaptive channel reassembly technique that reallocates the magnitude of outliers to other channels, thereby mitigating their impact on the quantization range.
- MixMix: All You Need for Data-Free Compression Are Feature and Data Mixing56
This work proposes MixMix based on two simple yet effective techniques, which outperforms existing methods on the mainstream compression tasks, including quantization, knowledge distillation and pruning, and proves the effectiveness of MixMix from both theoretical and empirical perspectives.
- Once Quantization-Aware Training: High Performance Extremely Low-bit Architecture Search53
This work proposes to combine Network Architecture Search methods with quantization with a shared step size to acquire a large number of quantized models and introduces a bit-inheritance scheme, which further reduces the time cost and meanwhile improves the quantization accuracy.
- 47
- Generating Transferable Adversarial Examples against Vision Transformers43
An Architecture-oriented Transferable Attacking (ATA) framework is proposed to generate transferable adversarial examples by activating the uncertain attention and perturbing the sensitive embedding to activate strong attacking transferability among diverse ViTs.
- 42
- 41
- Balanced Binary Neural Networks with Gated Residual41
This paper attempts to maintain the information propagated in the forward process and proposes a Balanced Binary Neural Networks with Gated Residual (BBG for short), a weight balanced binarization is introduced and thus the informative binary weights can capture more information contained in the activations.
- 38
- Exploring the Relationship between Architecture and Adversarially Robust Generalization30
This paper comprehensively evaluated 20 adversarially trained architectures on ImageNette and CIFAR-10 datasets towards several adversaries, and found that Vision Transformers often yield better adversarially robust generalization.
- SenseNova-U1: Unifying Multimodal Understanding and Generation with NEO-unify Architecture28
This work introduces SenseNova-U1, a native unified multimodal paradigm built upon NEO-unify, in which understanding and generation evolve as synergistic views of a single underlying process that points toward a broader roadmap where models do not translate between modalities, but think and act across them in a native manner.
- Exploring the Relationship Between Architectural Design and Adversarially Robust Generalization27
It is revealed that the higher weight sparsity contributes significantly towards the better adversarially robust generalization of Transformers, which can be often achieved by the specially-designed attention blocks, which could help to better understand the mechanism for designing robust DNNs.
- 23
- 22
- 21
- 20
- NNLQP: A Multi-Platform Neural Network Latency Query and Prediction System with An Evolving Database17
Publication data from OpenAlex, with missing venues and authors filled in from Crossref; citation counts are the higher of OpenAlex and Semantic Scholar, last synced 2026-10-13. One-sentence summaries under some papers are written by Semantic Scholar’s model. Citation counts may be lower than on Google Scholar, which indexes more sources.
Report an error
Wrong papers, two people merged into one, or a profile that should not be here? Tell us and we will fix or hide it.