The emergence of accurate open large language models (LLMs) has sparked a push for advanced quantization techniques to enable efficient deployment on end-user devices. In this paper, we revisit the challenge of extreme LLM compression---targeting ultra-low-bit quantization for both activations and weights---from a Fourier frequency domain perspective. We propose SpecQuant, a two-stage framework that tackles activation outliers and cross-channel variance. In the first stage, activation outliers are smoothed and transferred into the weight matrix to simplify downstream quantization. In the second stage, we apply channel-wise low-frequency Fourier truncation to suppress high-frequency components while preserving essential signal energy, improving quantization robustness. Our method builds on the principle that most of the weight energy is concentrated in low-frequency components, which can be retained with minimal impact on model accuracy. To enable runtime adaptability, we introduce a lightweight truncation module during inference that adjusts truncation thresholds based on channel characteristics. On LLaMA-3 8B, SpecQuant achieves 4-bit quantization for both weights and activations, narrowing the zero-shot accuracy gap to only 1.5% compared to full precision, while delivering 2× faster inference and 3× lower memory usage.

Large language models (LLMs) have driven major progress in NLP, yet their substantial memory and compute demands still hinder practical deployment.Binarization can compress weights to 1 bit, fundamentally lowering compute and bandwidth cost.However, existing methods cannot address activation heavy tails and thus must keep activations in high precision, preventing true end-to-end acceleration.To overcome this limitation, we propose BWLA (Binarized Weights and Low-bit Activations), the first post-training quantization framework that preserves high accuracy while achieving 1-bit weight quantization together with low-bit activations (e.g., 6 bits).The Orthogonal-Kronecker Transformation (OKT) learns an orthogonal mapping via EM minimization, converting unimodal weights into symmetric bimodal forms while suppressing activation tails and incoherence.The Proximal SVD Projection (PSP) then performs lightweight low-rank refinement through proximal SVD projection, further enhancing quantizability with minimal overhead.On Qwen3-32B, BWLA reaches a Wikitext2 perplexity of 11.92 under 6-bit activations (vs.38 from SOTA), improves five zero-shot tasks by more than 70%, and delivers 3.26× inference speedup, demonstrating strong potential for real-world LLM compression and acceleration.The code will be available at BWLA.

Transformer-based models have revolutionized computer vision (CV) and natural language processing (NLP) by achieving state-of-the-art performance across a range of benchmarks. However, nonlinear operations in models significantly contribute to inference latency, presenting unique challenges for efficient hardware acceleration. To this end, we propose QUARK, a quantization-enabled FPGA acceleration framework that leverages common patterns in nonlinear operations to enable efficient circuit sharing, thereby reducing hardware resource requirements. QUARK targets all nonlinear operations within Transformer-based models, achieving high-performance approximation through a novel circuit-sharing design tailored to accelerate these operations. Our evaluation demonstrates that QUARK significantly reduces the computational overhead of nonlinear operators in mainstream Transformer architectures, achieving up to a 1.96× end-to-end speedup over GPU implementations. Moreover, QUARK lowers the hardware overhead of nonlinear modules by more than 50% compared to prior approaches, all while maintaining high model accuracy—and even substantially boosting accuracy under ultra-low-bit quantization.

MOTIVATION: Molecular recognition between biological macromolecules and organic small molecules plays an important role in various life processes. Both structural information and binding data of biomolecular complexes are indispensable for depicting the underlying mechanism in such an event. The PDBbind database was created to collect experimentally measured binding data for the biomolecular complexes throughout the Protein Data Bank (PDB). It thus provides the linkage between structural information and energetic properties of biomolecular complexes, which is especially desirable for computational studies or statistical analyses. RESULTS: Since its first public release in 2004, the PDBbind database has been updated on an annual basis. The latest release (version 2013) provides experimental binding affinity data for 10,776 biomolecular complexes in PDB, including 8302 protein-ligand complexes and 2474 other types of complexes. In this article, we will describe the current methods used for compiling PDBbind and the updated status of this database. We will also review some typical applications of PDBbind published in the scientific literature. AVAILABILITY AND IMPLEMENTATION: All contents of this database are freely accessible at the PDBbind-CN Web server at http://www.pdbbind-cn.org/. CONTACT: [email protected]. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Most of the existing literature which has entirely focused on clustering nodes in large-scale networks. To discover multi-scale overlapping communities quickly, we propose a highly efficient multi-resolution link community detection algorithm to detect the link communities in massive networks based on the idea of edge labeling. First, we will get the node partition of the network based on a new multi-resolution node detection algorithm. After that, we can find the link community in a linear time by the labels of nodes. Its time complexity is near linear and its space complexity is linear. The effectiveness of our algorithm is demonstrated by extensive experiments on lots of computer generated artificial graphs and real-world networks. The results show that our algorithm is very fast and highly reliable. Tests on real and artificial networks also give excellent results comparing with the newly proposed link partition algorithm.