Molecular dynamics simulations can generate atomically detailed trajectories of complex systems, but analyzing these dynamics can be challenging when systems lack well-established quantitative descriptors (features). Graph neural networks (GNNs) in which messages are passed between nodes that represent atoms that are spatial neighbors promise to obviate manual feature engineering, but the use of GNNs with biomolecular systems of more than a few hundred residues has been limited in the context of analyzing dynamics by both difficulties in capturing the details of long-range interactions with message passing and the memory and runtime requirements associated with large graphs. Here, we show how local information can be aggregated to reduce memory and runtime requirements without sacrificing atomic detail. We demonstrate that this approach opens the door to analyzing simulations of protein-nucleic acid complexes with thousands of residues on single GPUs within minutes. For systems with hundreds of residues, for which there are sufficient data to make quantitative comparisons, we show that the approach improves performance and interpretability.

Current language model safety paradigms often fall short in emotionally charged or high-stakes settings, where refusal-only approaches may alienate users and naive compliance can amplify risk. We propose ProSocialAlign, a test-time, parameter-efficient framework that steers generation toward safe, empathetic, and value-aligned responses without retraining the base model. We formalize five human-centered objectives and cast safety as lexicographic constrained generation: first, applying hard constraints to eliminate harmful continuations; then optimizing for prosocial quality within the safe set. Our method combines (i) directional regulation, a harm-mitigation mechanism that subtracts a learned "harm vector" in parameter space, and (ii) preference-aware autoregressive reward modeling trained jointly across attributes with gradient conflict resolution, enabling fine-grained, user-controllable decoding. Empirical evaluations across five safety benchmarks demonstrate state-of-the-art performance, reducing unsafe leakage and boosting alignment to human values, with strong gains across multiple evaluation metrics. ProSocialAlign offers a robust and modular foundation for generating context-sensitive, safe, and human-aligned responses at inference time.

Understanding how protein mutations affect protein structure is essential for advancements in computational biology and bioinformatics. We introduce PRIMRose, a novel approach that predicts energy values for each residue given a mutated protein sequence. Unlike previous models that assess global energy shifts, our method analyzes the localized energetic impact of double amino acid insertions or deletions (InDels) at the individual residue level, enabling residue-specific insights into structural and functional disruption. We implement a Convolutional Neural Network architecture to predict the energy changes of each residue in a protein mutation. We train our model on datasets constructed from nine proteins, grouped into three categories: one set with exhaustive double InDel mutations, another with approximately 145k randomly sampled double InDel mutations, and a third with approximately 80k randomly sampled double InDel mutations. Our model achieves high predictive accuracy across a range of energy metrics as calculated by the Rosetta molecular modeling suite and reveals localized patterns that influence model performance, such as solvent accessibility and secondary structure context. This per-residue analysis offers new insights into the mutational tolerance of specific regions within proteins and provides higher interpretable and biologically meaningful predictions of InDels' effects.

Multihop Question Answering (QA) requires systems to identify and synthesize information from multiple text passages. While most prior retrieval methods assist in identifying relevant passages for QA, further assessing the utility of the passages can help in removing redundant ones, which may otherwise add to noise and inaccuracies in the generated answers. Existing utility prediction approaches model passage utility independently, overlooking a critical aspect of multihop reasoning: the utility of a passage can be context-dependent, influenced by its relation to other passages - whether it provides complementary information or forms a crucial link in conjunction with others. In this paper, we propose a lightweight approach to model contextual passage utility, accounting for inter-passage dependencies. We fine-tune a small transformer-based model to predict passage utility scores for multihop QA. We leverage the reasoning traces from an advanced reasoning model to capture the order in which passages are used to answer a question and obtain synthetic training data. Through comprehensive experiments, we demonstrate that our utility-based scoring of retrieved passages leads to improved reranking and downstream QA performance compared to relevance-based reranking methods.

Abstract--Attention-based large language models (LLMs) have transformed modern AI applications, but the quadratic cost of self-attention imposes significant compute and memory overhead. Dynamic sparsity (DS) attention mitigates this, yet its hardware efficiency is limited by the added prediction stage and the heavy memory traffic it entails. T o address these limitations, this paper proposes BitStopper, a fine-grained algorithm-architecture co-design that operates without a sparsity predictor . First, a bit-serial enable stage fusion (BESF) mechanism is proposed to reuse and minimize the memory access by progressively terminating trivial tokens and merging the prediction stage into the execution stage. Second, a lightweight and adaptive token selection (LA TS) strategy is developed to work in concert with the bit-level sparsity speculation. Third, a bit-level asynchronous processing (BAP) strategy is employed to improve compute utilization during the on-demand bit-grained memory fetching. Finally, an elaborate architecture is designed to translate the theoretical complexity reduction into practical performance improvement. Extensive evaluations demonstrate that, compared to state-of-the-art (SOT A) Transformer accelerators, BitStopper achieves 2.03 and 1.89 speedups over Sanger and SOF A, respectively, while delivering 2.4 and 2.1 improvements in energy efficiency.

Large language models (LLMs) are increasingly deployed on edge devices. To meet strict resource constraints, real-world deployment has pushed LLM quantization from 8-bit to 4-bit, 2-bit, and now 1.58-bit. Combined with lookup table (LUT)-based inference, CPUs run these ultra-low-bit LLMs even faster than NPUs, opening new opportunities for ubiquitous on-device intelligence. However, this paper identifies that LUT-based inference underutilizes memory bandwidth during parallel inference, which is required for prefilling, test-time scaling, and other multi-token scenarios. The root cause is the scalar LUT paradigm, which performs repetitive and non-contiguous memory accesses for each token. To solve the issue, we propose vector LUT, a new lookup paradigm that constructs a unified LUT across parallel tokens, and performs a single $1 \rightarrow N$ lookup per index. To realize it efficiently, we further introduce (1) Vector LUT-Centric Tensor Layout, and (2) Cache-Aware Streamed Lookup techniques. Evaluations on 5 edge devices across 3 LLMs show that Vec-LUT outperforms state-of-the-art baselines by up to $4.2\times$. Our implementation is integrated into llama.cpp. The code is available at https://github.com/Cipherxzc/vlut.cpp.

Neural Network Pruning has been established as driving force in the exploration of memory and energy efficient solutions with high throughput both during training and at test time. In this paper, we introduce a novel criterion for model compression, named "Expressiveness". Unlike existing pruning methods that rely on the inherent "Importance" of neurons' and filters' weights, ``Expressiveness" emphasizes a neuron's or group of neurons ability to redistribute informational resources effectively, based on the overlap of activations. This characteristic is strongly correlated to a network's initialization state, establishing criterion autonomy from the learning state stateless and thus setting a new fundamental basis for the expansion of compression strategies in regards to the "When to Prune" question. We show that expressiveness is effectively approximated with arbitrary data or limited dataset's representative samples, making ground for the exploration of Data-Agnostic strategies. Our work also facilitates a "hybrid" formulation of expressiveness and importance-based pruning strategies, illustrating their complementary benefits and delivering up to 10x extra gains w.r.t. weight-based approaches in parameter compression ratios, with an average of 1% in performance degradation. We also show that employing expressiveness (independently) for pruning leads to an improvement over top-performing and foundational methods in terms of compression efficiency. Finally, on YOLOv8, we achieve a 46.1% MACs reduction by removing 55.4\% of the parameters, with an increase of 3% in the mean Absolute Precision ($mAP_{50-95}$) for object detection on COCO dataset.

Preparticipation cardiovascular examination (PPCE) aims to prevent sudden cardiac death (SCD) by identifying athletes with structural or electrical cardiac abnormalities. Anthropometric measurements, such as waist circumference, limb lengths, and torso proportions to detect Marfan syndrome, can indicate elevated cardiovascular risk. Traditional manual methods are labor-intensive, operator-dependent, and challenging to scale. We present a fully automated deep-learning approach to estimate five key anthropometric measurements from 2D synthetic human body images. Using a dataset of 100,000 images derived from 3D body meshes, we trained and evaluated VGG19, ResNet50, and DenseNet121 with fully connected layers for regression. All models achieved sub-centimeter accuracy, with ResNet50 performing best, achieving a mean MAE of 0.668 cm across all measurements. Our results demonstrate that deep learning can deliver accurate anthropometric data at scale, offering a practical tool to complement athlete screening protocols. Future work will validate the models on real-world images to extend applicability.

Proper initialisation strategy is of primary importance to mitigate gradient explosion or vanishing when training neural networks. Yet, the impact of initialisation parameters still lacks a precise theoretical understanding for several well-established architectures. Here, we propose a new initialisation for networks with sinusoidal activation functions such as \texttt{SIREN}, focusing on gradients control, their scaling with network depth, their impact on training and on generalization. To achieve this, we identify a closed-form expression for the initialisation of the parameters, differing from the original \texttt{SIREN} scheme. This expression is derived from fixed points obtained through the convergence of pre-activation distribution and the variance of Jacobian sequences. Controlling both gradients and targeting vanishing pre-activation helps preventing the emergence of inappropriate frequencies during estimation, thereby improving generalization. We further show that this initialisation strongly influences training dynamics through the Neural Tangent Kernel framework (NTK). Finally, we benchmark \texttt{SIREN} with the proposed initialisation against the original scheme and other baselines on function fitting and image reconstruction. The new initialisation consistently outperforms state-of-the-art methods across a wide range of reconstruction tasks, including those involving physics-informed neural networks.

Recent advances in autoregressive (AR) generative models have produced increasingly powerful systems for media synthesis. Among them, next-scale prediction has emerged as a popular paradigm, where models generate images in a coarse-to-fine manner. However, scale-wise AR models suffer from exposure bias, which undermines generation quality. We identify two primary causes of this issue: (1) train-test mismatch, where the model must rely on its own imperfect predictions during inference, and (2) imbalance in scale-wise learning difficulty, where certain scales exhibit disproportionately higher optimization complexity. Through a comprehensive analysis of training dynamics, we propose Self-Autoregressive Refinement (SAR) to address these limitations. SAR introduces a Stagger-Scale Rollout (SSR) mechanism that performs lightweight autoregressive rollouts to expose the model to its own intermediate predictions, thereby aligning train-test patterns, and a complementary Contrastive Student-Forcing Loss (CSFL) that provides adequate supervision for self-generated contexts to ensure stable training. Experimental results show that applying SAR to pretrained AR models consistently improves generation quality with minimal computational overhead. For instance, SAR yields a 5.2% FID reduction on FlexVAR-d16 trained on ImageNet 256 within 10 epochs (5 hours on 32xA100 GPUs). Given its efficiency, scalability, and effectiveness, we expect SAR to serve as a reliable post-training method for visual autoregressive generation.