arXiv:2605.03241v2 Announce Type: replace-cross Abstract: Read-only memory (ROM) provides deterministic access to predefined data mappings. Extending ROM concepts to the optical domain enables high-bandwidth, low-latency, and parallel memory access, but realizing compact and reconfigurable optical ROM remains challenging due to loss, wavelength control, and integration constraints. This work presents a high-speed, reconfigurable photonic ROM architecture […]
Memory-Efficient LLM Pretraining via Minimalist Optimizer Design
arXiv:2506.16659v3 Announce Type: replace-cross Abstract: Training large language models (LLMs) relies on adaptive optimizers such as Adam, which introduce extra operations and require significantly more memory to maintain first- and second-order moments than SGD. While recent works such as GaLore, Fira and APOLLO have proposed state-compressed memory-efficient variants, a fundamental question remains: What are the […]
SiameseNorm: Breaking the Barrier to Reconciling Pre/Post-Norm
arXiv:2602.08064v2 Announce Type: replace-cross Abstract: The long-standing tension between Pre- and Post-Norm remains an open problem in Transformer architecture, reflecting a fundamental trade-off between training stability and representational capacity. Prior attempts to combine their strengths have made progress, but often show limited robustness across training settings, restricting their broader applicability. We revisit this dilemma, showing […]
Attacking the Spike: On the Transferability and Security of Spiking Neural Networks to Adversarial Examples
arXiv:2209.03358v5 Announce Type: replace-cross Abstract: Spiking neural networks (SNNs) have attracted much attention for their high energy efficiency and recent advances in classification performance. However, unlike traditional deep learning approaches, the study of SNN robustness to adversarial examples remains relatively underdeveloped. In this work, we advance the adversarial attack side of SNNs through three contributions. […]
StreetDesignAI: Broadening Designer Perspectives Through Multi-Persona Evaluation of Cycling Infrastructure
arXiv:2601.15671v3 Announce Type: replace-cross Abstract: Designing cycling infrastructure requires balancing the competing needs of diverse user groups, yet designers often struggle to anticipate how different cyclists experience the same street environment. We investigate how persona-based evaluation can support cycling infrastructure design by making experiential conflicts explicit during the design process. Informed by a formative study […]
Swift Sampling: Selecting Temporal Surprises via Taylor Series
arXiv:2605.22678v1 Announce Type: cross Abstract: While most frames in long-form video are redundant, the critical information resides in temporal surprises: moments where the actual visual features deviate from their predicted evolution. Inspired by the human brain’s predictive coding, we introduce Swift Sampling, an elegant, training-free frame selection algorithm that automatically identifies high-information moments in a […]
AI-Driven Prediction of Cancer Pain Episodes: A Hybrid Decision Support Approach
arXiv:2512.16739v2 Announce Type: replace Abstract: Lung cancer patients frequently experience breakthrough pain episodes, with up to 91% requiring timely intervention. To enable proactive pain management, we propose a hybrid machine learning and large language model pipeline that predicts pain episodes within 48 and 72 hours of hospitalization using both structured and unstructured electronic health record […]
The Neural Compiler: Program-to-Network Translation for Hybrid Scientific Machine Learning
arXiv:2605.22498v1 Announce Type: cross Abstract: Scientific machine learning often requires combining known physics with unknown parameters or correction terms learned from data. Existing approaches either ignore known structure, encode it as a soft penalty, or require hand-written PyTorch code for each equation. We present The Neural Compiler, a system that translates programs written in a […]
DeltaBox: Scaling Stateful AI Agents with Millisecond-Level Sandbox Checkpoint/Rollback
arXiv:2605.22781v1 Announce Type: cross Abstract: LLM-powered AI agents require high-frequency state exploration (e.g., test-time tree search and reinforcement learning), relying on rapid checkpoint and rollback (C/R) of the complete sandbox state, including files and process state (e.g., memory, contexts, etc.). Existing mechanisms duplicate the entire state, causing hundreds of milliseconds to seconds of latency per […]
U-CECE: A Universal Multi-Resolution Framework for Conceptual Counterfactual Explanations
arXiv:2604.08295v3 Announce Type: replace Abstract: As AI models grow more complex, explainability is essential for building trust, yet concept-based counterfactual methods still face a trade-off between expressivity and efficiency. Representing underlying concepts as atomic sets is fast but misses relational context, whereas full graph representations are more faithful but require solving the NP-hard Graph Edit […]
Decision Potential Surface: A Theoretical and Practical Approximation of Large Language Model Decision Boundary
arXiv:2510.03271v2 Announce Type: replace-cross Abstract: Decision boundary, the subspace of inputs where a machine learning model assigns equal classification probabilities to two classes, is pivotal in revealing core model properties and interpreting behaviors. While analyzing the decision boundary of large language models (LLMs) has attracted increasing attention recently, constructing it for mainstream LLMs remains computationally […]
Twice Sequential Monte Carlo for Tree Search
arXiv:2511.14220v3 Announce Type: replace-cross Abstract: Model-based reinforcement learning (RL) methods that leverage search are responsible for many milestone breakthroughs in RL. Sequential Monte Carlo (SMC) recently emerged as an alternative to the Monte Carlo Tree Search (MCTS) algorithm which drove these breakthroughs. SMC is easier to parallelize and more suitable to GPU acceleration. However, it […]