Hi everyone, I’m a 2nd-year CS student. For my latest independent study, I wanted to see how State Space Models (Mamba) compare to LSTMs when dealing with high-entropy time series, specifically, finding hidden ‘Iceberg’ orders in a noisy limit order book. I built a ‘Frozen Chaos’ simulation engine to bench both architectures on signal efficiency and OOD resilience. Key Findings from Phase 1: ‘Fail-Fast’ Logic: In a ‘Pure Drain’ stress test (zero signal), the LSTM suffered from state-locking, […]

Ver mais

arXiv:2602.16823v1 Announce Type: new Abstract: *Automated circuit discovery* is a central tool in mechanistic interpretability for identifying the internal components of neural networks responsible for specific behaviors. While prior methods have made significant progress, they typically depend on heuristics or approximations and do not offer provable guarantees over continuous input domains for the resulting circuits. In this work, we leverage recent advances in neural network verification to propose a suite of automated algorithms that yield circuits with *provable […]

Ver mais

Existing value-based online reinforcement learning (RL) algorithms suffer from slow policy exploitation due to ineffective exploration and delayed policy updates. To address these challenges, we propose an algorithm called Instant Retrospect Action (IRA). Specifically, we propose Q-Representation Discrepancy Evolution (RDE) to facilitate Q-network representation learning, enabling discriminative representations for neighboring state-action pairs. In addition, we adopt an explicit method to policy constraints by enabling Greedy Action Guidance (GAG). This is achieved through backtracking historical actions, which effectively enhances […]

Ver mais

Adversarial training attains strong empirical robustness to specific adversarial attacks by training on concrete adversarial perturbations, but it produces neural networks that are not amenable to strong robustness certificates through neural network verification. On the other hand, earlier certified training schemes directly train on bounds from network relaxations to obtain models that are certifiably robust, but display sub-par standard performance. Recent work has shown that state-of-the-art trade-offs between certified robustness and standard performance can be obtained through a […]

Ver mais

arXiv:2601.16434v1 Announce Type: new Abstract: Infrared small target detection (IRSTD) plays a crucial role in numerous military and civilian applications. However, existing methods often face the gradual degradation of target edge pixels as the number of network layers increases, and traditional convolution struggles to differentiate between frequency components during feature extraction, leading to low-frequency backgrounds interfering with high-frequency targets and high-frequency noise triggering false detections. To address these limitations, we propose MDAFNet (Multi-scale Differential Edge and Adaptive Frequency […]

Ver mais

arXiv:2502.04591v4 Announce Type: replace-cross Abstract: Oversmoothing is a fundamental challenge in graph neural networks (GNNs): as the number of layers increases, node embeddings become increasingly similar, and model performance drops sharply. Traditionally, oversmoothing has been quantified using metrics that measure the similarity of neighbouring node features, such as the Dirichlet energy. We argue that these metrics have critical limitations and fail to reliably capture oversmoothing in realistic scenarios. For instance, they provide meaningful insights only for very deep […]

Ver mais

Most documentation on the web is written for humans. HTML pages, navigation, prose, repetition. All interface artifacts. Agents don’t need any of that. When agents “learn from docs”, they’re reasoning over a rendering format, not the underlying technical truth. That’s why context breaks and hallucinations show up. Not a model problem. A substrate problem. At Brane, we’ve been working on agent memory and coordination. One conclusion kept repeating. The real bottleneck isn’t intelligence. It’s context and memory infrastructure. […]

Ver mais

arXiv:2602.23469v1 Announce Type: new Abstract: There is a growing demand for supporting inference queries that combine Structured Query Language (SQL) and Artificial Intelligence / Machine Learning (AI/ML) model inferences in database systems, to avoid data denormalization and transfer, facilitate management, and alleviate privacy concerns. Co-optimization techniques for executing inference queries in database systems without accuracy loss fall into four categories: (O1) Relational algebra optimization treating AI/ML models as black-box user-defined functions (UDFs); (O2) Factorized AI/ML inferences; (O3) Tensor-relational […]

Ver mais

arXiv:2312.10424v4 Announce Type: replace-cross Abstract: We derive uniform all-time concentration bound of the type ‘for all $n geq n_0$ for some $n_0$’ for TD(0) with linear function approximation. We work with online TD learning with samples from a single sample path of the underlying Markov chain. This makes our analysis significantly different from offline TD learning or TD learning with access to independent samples from the stationary distribution of the Markov chain. We treat TD(0) as a contractive […]

Ver mais

arXiv:2602.06179v1 Announce Type: new Abstract: Pelvic diseases in women of reproductive age represent a major global health burden, with diagnosis frequently delayed due to high anatomical variability, complicating MRI interpretation. Existing AI approaches are largely disease-specific and lack real-time compatibility, limiting generalizability and clinical integration. To address these challenges, we establish a benchmark framework for disease- and parameter-agnostic, real-time-compatible unsupervised anomaly detection in pelvic MRI. The method uses a residual variational autoencoder trained exclusively on healthy sagittal T2-weighted […]

Ver mais