technocracy

arXiv:2603.23637v1 Announce Type: new Abstract: Ray-tracing-based 3D Gaussian splatting (3DGS) methods overcome the limitations of rasterization — rigid pinhole camera assumptions, inaccurate shadows, and lack of native reflection or refraction — but remain slower due to the cost of sorting all intersecting Gaussians along every ray. Moreover, existing ray-tracing methods still rely on rasterization-style approximations such as shadow mapping for relightable scenes, undermining the generality that ray tracing promises. We present a differentiable, sorting-free stochastic formulation for ray-traced […]

Ver mais

arXiv:2604.15448v1 Announce Type: new Abstract: Foundational optimization embeddings have recently emerged as powerful pre-trained representations for mixed-integer programming (MIP) problems. These embeddings were shown to enable cross-domain transfer and reduce reliance on solver-generated labels. In this work, we investigate whether such representations generalize beyond optimization to decision problems, focusing on Boolean satisfiability (SAT). We adapt the foundational optimization architecture to SAT by mapping CNF formulas into the same bipartite constraint-variable graph representation used for MIPs. This allows direct […]

Ver mais

arXiv:2601.10809v1 Announce Type: new Abstract: Style features such as friendly, helpful, or concise are widely used in prompts to steer the behavior of Large Language Model (LLM) conversational agents, yet their unintended side effects remain poorly understood. In this work, we present the first systematic study of cross-feature stylistic side effects. We conduct a comprehensive survey of 127 conversational agent papers from ACL Anthology and identify 12 frequently used style features. Using controlled, synthetic dialogues across task-oriented and […]

Ver mais

I am working on a peg-in-hole robotic assembly thesis with a Doosan M1013, ROS2 & an eye-in-hand RGB-D camera. The upstream perception system gives a coarse hole/block pose from stationary RGB-D cameras. Based on prior measurements/error propagation, the pre-insertion uncertainty may be around 3–5 mm average and up to 7–11 mm worst case, with about 1–2° angular error. I want to train a contact-rich insertion policy using vision + force/torque + proprioception, starting from a pre-insert pose about […]

Ver mais

In this tutorial, we work with the Fable 5 Traces dataset from Hugging Face and build a complete workflow around real coding-agent trace data. We start by setting up a lightweight environment that avoids fragile dependencies such as datasets, scikit-learn, and scipy. Then we manually download and parse the merged JSONL file to keep the notebook stable in Colab. From there, we inspect repository files, preview raw trace examples, normalize tool calls and text outputs, audit the dataset […]

Ver mais

Recently, some of my mentees—freshmen in college—asked me the question everyone is thinking: “If AI is going to disrupt everything, is it even worth pursuing Computer Science? What do we even do? If there are going to be no jobs in the future, what is the point?” This reminded me of a recent insight from Andrej Karpathy: “I often say that pre-AGI education is useful. Post-AGI education is fun. In a similar way, people go to the gym […]

Ver mais

arXiv:2603.12485v1 Announce Type: new Abstract: GPUs play an increasingly important role in modern software. However, the heterogeneous host-device execution model and expanding software stacks make GPU programs prone to memory-safety and concurrency bugs that evade static analysis. While fuzz-testing, combined with dynamic error checking tools, offers a plausible solution, it remains underutilized for GPUs. In this work, we identify three main obstacles limiting prior GPU fuzzing efforts: (1) kernel-level fuzzing leading to false positives, (2) lack of device-side […]

Ver mais

arXiv:2601.00095v1 Announce Type: new Abstract: Large language models increasingly require structured inference, from JSON schema enforcement to multi-lingual parsing, where outputs must satisfy complex constraints. We introduce MetaJuLS, a meta-reinforcement learning approach that learns universal constraint propagation policies applicable across languages and tasks without task-specific retraining. By formulating structured inference as adaptive constraint propagation and training a Graph Attention Network with meta-learning, MetaJuLS achieves 1.5–2.0$times$ speedups over GPU-optimized baselines while maintaining within 0.2% accuracy of state-of-the-art parsers. On […]

Ver mais