Hi everyone, I wanted to share the architecture of a 2-year project I led: optimizing a line-haul logistics network using a hybrid of Multi-Agent RL (MARL) and Linear Programming (LP). We were trying to optimize a live and complex delivery network with dynamically arriving requests. We built a hierarchical architecture to get the best of both worlds (standard OR and RL): The “Fleet Manager” (MARL): PPO agents handle the high-level decision-making. The agent decides which cluster of orders […]

Ver mais

We study Constrained Online Convex Optimization (COCO), where a learner chooses actions iteratively, observes both unanticipated convex loss and convex constraint, and accumulates loss while incurring penalties for constraint violations. We introduce CLASP (Convex Losses And Squared Penalties), an algorithm that minimizes cumulative loss together with squared constraint violations. Our analysis departs from prior work by fully leveraging the firm non-expansiveness of convex projectors, a proof strategy not previously applied in this setting. For convex losses, CLASP achieves […]

Ver mais

arXiv:2601.19952v1 Announce Type: new Abstract: Real-time voice agents face a dilemma: end-to-end models often lack deep reasoning, while cascaded pipelines incur high latency by executing ASR, LLM reasoning, and TTS strictly in sequence, unlike human conversation where listeners often start thinking before the speaker finishes. Since cascaded architectures remain the dominant choice for complex tasks, existing cascaded streaming strategies attempt to reduce this latency via mechanical segmentation (e.g., fixed chunks, VAD-based splitting) or speculative generation, but they frequently […]

Ver mais

arXiv:2604.14232v1 Announce Type: new Abstract: The Spatial-Temporal Graph Attention Network (ST-GAT) framework was created to serve as an explainable GNN-based solution for detecting bank distress early warning signs and for conducting macro-prudential surveillance of the interbank system in the United States. The ST-GAT framework models 8,103 FDIC insured institutions across 58 quarterly snapshots (2010Q1-2024Q2). Bilateral exposures were reconstructed from publicly available FDIC Call Reports using maximum entropy estimation to produce a dynamic directed weighted graph. The framework achieves […]

Ver mais

arXiv:2603.25791v1 Announce Type: new Abstract: Existing hand-object interactions (HOI) methods are largely limited to rigid objects, while 4D reconstruction methods of articulated objects generally require pre-scanning the object or even multi-view videos. It remains an unexplored but significant challenge to reconstruct 4D human-articulated-object interactions from a single monocular RGB video. Fortunately, recent advancements in foundation models present a new opportunity to address this highly ill-posed problem. To this end, we introduce ArtHOI, an optimization-based framework that integrates and […]

Ver mais

:::info Astounding Stories of Super-Science April 2004, by Astounding Stories is part of HackerNoon’s Book Blog Post series. You can jump to any chapter in this book here. THE COUNTRY OF THE BLIND – III. — THE STOLEN BACILLUS. Astounding Stories of Super-Science April 2004: THE COUNTRY OF THE BLIND – III. — THE STOLEN BACILLUS. By H. G. Wells ::: “This again,” said the Bacteriologist, slipping a glass slide under the microscope, “is well,—a preparation of the Bacillus […]

Ver mais

arXiv:2602.17680v1 Announce Type: new Abstract: Existing Protein Language Models (PLMs) often suffer from limited adaptability to multiple tasks and exhibit poor generalization across diverse biological contexts. In contrast, general-purpose Large Language Models (LLMs) lack the capability to interpret protein sequences and fall short in domain-specific knowledge, limiting their capacity for effective biosemantic reasoning. To combine the advantages of both, we propose BioBridge, a domain-adaptive continual pretraining framework for protein understanding. This framework employs Domain-Incremental Continual Pre-training (DICP) to […]

Ver mais

The volume of scientific submissions continues to climb, outpacing the capacity of qualified human referees and stretching editorial timelines. At the same time, modern large language models (LLMs) offer impressive capabilities in summarization, fact checking, and literature triage, making the integration of AI into peer review increasingly attractive—and, in practice, unavoidable. Yet early deployments and informal adoption have exposed acute failure modes. Recent incidents have revealed that hidden prompt injections embedded in manuscripts can steer AI-generated reviews toward […]

Ver mais

Effective exploration is a key challenge in reinforcement learning for large language models: discovering high-quality trajectories within a limited sampling budget from the vast natural language sequence space. Existing methods face notable limitations: GRPO samples exclusively from the root, saturating high-probability trajectories while leaving deep, error-prone states under-explored. Tree-based methods blindly disperse budgets across trivial or unrecoverable states, causing sampling dilution that fails to uncover rare correct suffixes and destabilizes local baselines. To address this, we propose Deep […]

Ver mais

arXiv:2604.15357v1 Announce Type: new Abstract: Precise estimation of model inference latency is crucial for time-critical mobile edge applications, enabling devices to calculate latency margins against deadlines and trade them for enhanced model performance or resource savings. However, the ubiquity of Dynamic Voltage and Frequency Scaling (DVFS) renders traditional static profiling invalid in real-world deployments, as inference latency fluctuates with varying processor (CPU and GPU) frequencies. While extensive profiling across frequency combinations is theoretically possible, it is prohibitively expensive, […]

Ver mais