arXiv:2602.02546v1 Announce Type: new Abstract: Large language models (LLMs) deliver strong performance, but their high compute and memory costs make deployment difficult in resource-constrained scenarios. Weight-only post-training quantization (PTQ) is appealing, as it reduces memory usage and enables practical speedup without low-bit operators or specialized hardware. However, accuracy often degrades significantly in weight-only PTQ at sub-4-bit precision, and our analysis identifies two main causes: (1) down-projection matrices are a well-known quantization bottleneck, but maintaining their fidelity often requires […]

Ver mais

arXiv:2601.12254v1 Announce Type: new Abstract: Generative speech enhancement (GSE) models show great promise in producing high-quality clean speech from noisy inputs, enabling applications such as curating noisy text-to-speech (TTS) datasets into high-quality ones. However, GSE models are prone to hallucination errors, such as phoneme omissions and speaker inconsistency, which conventional error filtering based on non-intrusive speech quality metrics often fails to detect. To address this issue, we propose a non-intrusive method for filtering hallucination errors from discrete token-based […]

Ver mais

In today’s cloud-native and AI-driven enterprise landscape, system failures are no longer caused by simple outages but by complex interactions between microservices, automation, and machine-learning models. To understand how explainable AI can transform reliability engineering, we spoke with Adithya Jakkaraju who authored the IEEE International Conference on Advances in Next-Generation Computer Science (ICANCS) 2025 Best Paper, “Explainable AI for Resilient Microservices: A Transparency-Driven Approach,” which presents a practical framework for building trustworthy, auditable AI-driven resilience in large-scale systems. […]

Ver mais

Accurately quantifying terrestrial carbon exchange is essential for climate policy and carbon accounting, yet models must generalize to ecosystems underrepresented in sparse eddy covariance observations. Despite this challenge being a natural instance of zero-shot spatial transfer learning for time series regression, no standardized benchmark exists to rigorously evaluate model performance across geographically distinct locations with different climate regimes and vegetation types. We introduce CarbonBench, the first benchmark for zero-shot spatial transfer in carbon flux upscaling. CarbonBench comprises over […]

Ver mais

Pool-based sequential active learning for regression (ALR) optimally selects a small number of samples sequentially from a large pool of unlabeled samples to label, so that a more accurate regression model can be constructed under a given labeling budget. Representativeness and diversity, which involve computing the distances among different samples, are important considerations in ALR. However, previous ALR approaches do not incorporate the importance of different features in inter-sample distance computation, resulting in sub-optimal sample selection. This paper […]

Ver mais

arXiv:2603.20392v1 Announce Type: cross Abstract: Probabilistic circuit (PC) structure learning is hampered by greedy algorithms that make irreversible, locally optimal decisions. We propose SymCircuit, which replaces greedy search with a learned generative policy trained via entropy-regularized reinforcement learning. Instantiating the RL-as-inference framework in the PC domain, we show the optimal policy is a tempered Bayesian posterior, recovering the exact posterior when the regularization temperature is set inversely proportional to the dataset size. The policy is implemented as SymFormer, […]

Ver mais

We investigate the geometric structure of learning dynamics in overparameterized transformer models through carefully controlled modular arithmetic tasks. Our primary finding is that despite operating in high-dimensional parameter spaces ($d=128$), transformer training trajectories rapidly collapse onto low-dimensional execution manifolds of dimension $3$–$4$. This dimensional collapse is robust across random seeds and moderate task difficulties, though the orientation of the manifold in parameter space varies between runs. We demonstrate that this geometric structure underlies several empirically observed phenomena: (1) […]

Ver mais

arXiv:2601.07884v1 Announce Type: new Abstract: The proliferation of online social networks has significantly reshaped the way individuals access and engage with information. While these platforms offer unprecedented connectivity, they may foster environments where users are increasingly exposed to homogeneous content and like-minded interactions. Such dynamics are associated with selective exposure and the emergence of filter bubbles, echo chambers, tunnel vision, and polarization, which together can contribute to ideological isolation and raise concerns about information diversity and public discourse. […]

Ver mais

Imagine telling Claude: “Reply ‘Running 10 minutes late’ to Sarah and attach that funny cat meme I just uploaded.” Seconds later — done. No switching apps. No copy-pasting. Everything stays local, private, and scripted through natural language. That’s exactly what whatsapp-mcp-go enables. This lightweight, pure-Go project bridges your personal WhatsApp account to Claude Desktop (or Cursor) via the Model Context Protocol (MCP). Claude can read chats, search contacts, send messages (text, images, voice notes), and download media — […]

Ver mais