KVSharer: Efficient Inference via Layer-Wise Dissimilar KV Cache Sharing

The development of large language models (LLMs) has significantly expanded model sizes, resulting in substantial GPU memory requirements during inference. The key and value storage of the attention map in the KV (key-value) cache accounts for more than 80\% of this memory consumption. Nowadays, most existing KV cache compression methods focus on intra-layer compression within a single Transformer layer but few works consider layer-wise compression. In this paper, we propose a plug-and-play method called \textit{KVSharer}, which shares the KV cache between layers to achieve layer-wise compression. Rather than intuitively sharing based on higher similarity, we discover a counterintuitive phenomenon: sharing dissimilar KV caches better preserves the model performance. Experiments show that \textit{KVSharer} can reduce KV cache computation by 30\%, thereby lowering memory consumption without significantly impacting model performance and it can also achieve at least 1.3 times generation acceleration. Additionally, we verify that \textit{KVSharer} is compatible with existing intra-layer KV cache compression methods, and combining both can further save memory.

Lagrangian Motion Fields for Long-term Motion Generation

Long-term motion generation is a challenging task that requires producing coherent and realistic sequences over extended durations. Current methods primarily rely on framewise motion representations, which capture only static spatial details and overlook temporal dynamics. This approach leads to significant redundancy across the temporal dimension, complicating the generation of effective long-term motion. To overcome these limitations, we introduce the novel concept of Lagrangian Motion Fields, specifically designed for long-term motion generation. By treating each joint as a Lagrangian particle with uniform velocity over short intervals, our approach condenses motion representations into a series of "supermotions" (analogous to superpixels). This method seamlessly integrates static spatial information with interpretable temporal dynamics, transcending the limitations of existing network architectures and motion sequence content types. Our solution is versatile and lightweight, eliminating the need for neural network preprocessing. Our approach excels in tasks such as long-term music-to-dance generation and text-to-motion generation, offering enhanced efficiency, superior generation quality, and greater diversity compared to existing methods. Additionally, the adaptability of Lagrangian Motion Fields extends to applications like infinite motion looping and fine-grained controlled motion generation, highlighting its broad utility. Video demonstrations are available at \url{https://plyfager.github.io/LaMoG}.

Nothing in Excess: Mitigating the Exaggerated Safety for LLMs via Safety-Conscious Activation Steering

Safety alignment is indispensable for Large language models (LLMs) to defend threats from malicious instructions. However, recent researches reveal safety-aligned LLMs prone to reject benign queries due to the exaggerated safety issue, limiting their helpfulness. In this paper, we propose a Safety-Conscious Activation Steering (SCANS) method to mitigate the exaggerated safety concerns in aligned LLMs. First, SCANS extracts the refusal steering vectors within the activation space and utilizes vocabulary projection to anchor some specific safety-critical layers which influence model refusal behavior. Second, by tracking the hidden state transition, SCANS identifies the steering direction and steers the model behavior accordingly, achieving a balance between exaggerated safety and adequate safety. Experiments show that SCANS achieves new state-of-the-art performance on XSTest and OKTest benchmarks, without impairing their defense capability against harmful queries and maintaining almost unchanged model capability.

BatGPT-Chem: A Foundation Large Model For Retrosynthesis Prediction

Retrosynthesis analysis is pivotal yet challenging in drug discovery and organic chemistry. Despite the proliferation of computational tools over the past decade, AI-based systems often fall short in generalizing across diverse reaction types and exploring alternative synthetic pathways. This paper presents BatGPT-Chem, a large language model with 15 billion parameters, tailored for enhanced retrosynthesis prediction. Integrating chemical tasks via a unified framework of natural language and SMILES notation, this approach synthesizes extensive instructional data from an expansive chemical database. Employing both autoregressive and bidirectional training techniques across over one hundred million instances, BatGPT-Chem captures a broad spectrum of chemical knowledge, enabling precise prediction of reaction conditions and exhibiting strong zero-shot capabilities. Superior to existing AI methods, our model demonstrates significant advancements in generating effective strategies for complex molecules, as validated by stringent benchmark tests. BatGPT-Chem not only boosts the efficiency and creativity of retrosynthetic analysis but also establishes a new standard for computational tools in synthetic design. This development empowers chemists to adeptly address the synthesis of novel compounds, potentially expediting the innovation cycle in drug manufacturing and materials science. We release our trial platform at \url{https://www.batgpt.net/dapp/chem}.

Improving Hyperbolic Representations via Gromov-Wasserstein Regularization

Hyperbolic representations have shown remarkable efficacy in modeling inherent hierarchies and complexities within data structures. Hyperbolic neural networks have been commonly applied for learning such representations from data, but they often fall short in preserving the geometric structures of the original feature spaces. In response to this challenge, our work applies the Gromov-Wasserstein (GW) distance as a novel regularization mechanism within hyperbolic neural networks. The GW distance quantifies how well the original data structure is maintained after embedding the data in a hyperbolic space. Specifically, we explicitly treat the layers of the hyperbolic neural networks as a transport map and calculate the GW distance accordingly. We validate that the GW distance computed based on a training set well approximates the GW distance of the underlying data distribution. Our approach demonstrates consistent enhancements over current state-of-the-art methods across various tasks, including few-shot image classification, as well as semi-supervised graph link prediction and node classification.

Sparse Matrix Coding for URLLC

Sparse Vector Coding (SVC) has long been considered an encoding method that meets the URLLC QOS requirements. This encoding method has been widely studied and applied due to its low encoding and decoding complexity, no pilot transmission, resistance to inter-carrier interference, and low power consumption. However, due to the use of position indexing, the encoding essentially reduces the signal-to-noise ratio requirements by increasing the communication bandwidth, which also leads to low encoding efficiency and strong rigidity in decoding. Based on the sparse representation characteristics of SVC, we propose a joint sparse representation encoding, namely Sparse Matrix Coding (SMC). This encoding method utilizes multi-user information joint encoding, and the sparsity and sparse locations between users are shared.

$ν$-DBA: Neural Implicit Dense Bundle Adjustment Enables Image-Only Driving Scene Reconstruction

The joint optimization of the sensor trajectory and 3D map is a crucial characteristic of bundle adjustment (BA), essential for autonomous driving. This paper presents $\nu$-DBA, a novel framework implementing geometric dense bundle adjustment (DBA) using 3D neural implicit surfaces for map parametrization, which optimizes both the map surface and trajectory poses using geometric error guided by dense optical flow prediction. Additionally, we fine-tune the optical flow model with per-scene self-supervision to further improve the quality of the dense mapping. Our experimental results on multiple driving scene datasets demonstrate that our method achieves superior trajectory optimization and dense reconstruction accuracy. We also investigate the influences of photometric error and different neural geometric priors on the performance of surface reconstruction and novel view synthesis. Our method stands as a significant step towards leveraging neural implicit representations in dense bundle adjustment for more accurate trajectories and detailed environmental mapping.

Drag Your Noise: Interactive Point-based Editing via Diffusion Semantic Propagation

Point-based interactive editing serves as an essential tool to complement the controllability of existing generative models. A concurrent work, DragDiffusion, updates the diffusion latent map in response to user inputs, causing global latent map alterations. This results in imprecise preservation of the original content and unsuccessful editing due to gradient vanishing. In contrast, we present DragNoise, offering robust and accelerated editing without retracing the latent map. The core rationale of DragNoise lies in utilizing the predicted noise output of each U-Net as a semantic editor. This approach is grounded in two critical observations: firstly, the bottleneck features of U-Net inherently possess semantically rich features ideal for interactive editing; secondly, high-level semantics, established early in the denoising process, show minimal variation in subsequent stages. Leveraging these insights, DragNoise edits diffusion semantics in a single denoising step and efficiently propagates these changes, ensuring stability and efficiency in diffusion editing. Comparative experiments reveal that DragNoise achieves superior control and semantic retention, reducing the optimization time by over 50% compared to DragDiffusion. Our codes are available at https://github.com/haofengl/DragNoise.

Hypertext Entity Extraction in Webpage

Webpage entity extraction is a fundamental natural language processing task in both research and applications. Nowadays, the majority of webpage entity extraction models are trained on structured datasets which strive to retain textual content and its structure information. However, existing datasets all overlook the rich hypertext features (e.g., font color, font size) which show their effectiveness in previous works. To this end, we first collect a \textbf{H}ypertext \textbf{E}ntity \textbf{E}xtraction \textbf{D}ataset (\textit{HEED}) from the e-commerce domains, scraping both the text and the corresponding explicit hypertext features with high-quality manual entity annotations. Furthermore, we present the \textbf{Mo}E-based \textbf{E}ntity \textbf{E}xtraction \textbf{F}ramework (\textit{MoEEF}), which efficiently integrates multiple features to enhance model performance by Mixture of Experts and outperforms strong baselines, including the state-of-the-art small-scale models and GPT-3.5-turbo. Moreover, the effectiveness of hypertext features in \textit{HEED} and several model components in \textit{MoEEF} are analyzed.

Head-wise Shareable Attention for Large Language Models

Large Language Models (LLMs) suffer from huge number of parameters, which restricts their deployment on edge devices. Weight sharing is one promising solution that encourages weight reuse, effectively reducing memory usage with less performance drop. However, current weight sharing techniques primarily focus on small-scale models like BERT and employ coarse-grained sharing rules, e.g., layer-wise. This becomes limiting given the prevalence of LLMs and sharing an entire layer or block obviously diminishes the flexibility of weight sharing. In this paper, we present a perspective on $\textit{$\textbf{head-wise shareable attention for large language models}$}$. We further propose two memory-efficient methods that share parameters across attention heads, with a specific focus on LLMs. Both of them use the same dynamic strategy to select the shared weight matrices. The first method directly reuses the pre-trained weights without retraining, denoted as $\textbf{DirectShare}$. The second method first post-trains with constraint on weight matrix similarity and then shares, denoted as $\textbf{PostShare}$. Experimental results reveal our head-wise shared models still maintain satisfactory capabilities, demonstrating the feasibility of fine-grained weight sharing applied to LLMs.