Silytics Intelligence

Recent changes

Detected between refreshes of the original sources: licenses, names, descriptions, topics and tasks.

• All-St3R SLAM: Real-time RGB Dynamic SLAM with Pixel-wise Motion Masking · Topics1 h ago
• EvoSpatial: Experience-Driven Skill and Tool Evolution for Spatial Reasoning Agents · Description Tool-augmented vision-language agents compose perception and measurement to reason about spatial relationships, but effective execution also requires tracking geometric assumptions and checking intermediate evidence. Preserving this experie → Spatial reasoning agents can inspect tool outputs and repair errors, but reusing these lessons requires preserving both the computation and the conditions that make it valid. We introduce EvoSpatial, a framework that learns from execution e1 h ago
• SkillScreen: High-Recall Screening of Malicious Agent Skills with Decision Models · Description Agent skills turn natural-language instructions into actions, creating a security challenge: legitimate automation and malicious behaviour can look deceptively similar. A practical screen must catch nearly every attack while keeping the rev → Agent skills turn natural-language instructions into actions, creating a security challenge: legitimate automation and malicious behaviour can look deceptively similar. A practical screen must catch nearly every attack while keeping the rev1 h ago
• Interaction-as-a-Judge · Description Coding agents are tasked with producing sophisticated interactive applications such as websites, desktop applications, and games. While humans assess these applications interactively, current automated LLM evaluations primarily focus on cod → Coding agents are tasked with producing sophisticated interactive applications such as websites, desktop applications, and games. While humans assess these applications interactively, current automated LLM evaluations primarily focus on cod1 h ago
• ABot-ER: Unified Embodied Reasoning through Agentic Data-Model Co-Evolution · Description We introduce \textbf{ABot Embodied Reasoning (ABot-ER)}, a unified embodied reasoning foundation model that breaks the tension between breadth and depth in embodied reasoning. Embodied intelligence demands the joint mastery of perception, p → We introduce ABot Embodied Reasoning (ABot-ER), a unified embodied reasoning foundation model that breaks the tension between breadth and depth in embodied reasoning. Embodied intelligence demands the joint mastery of perception, planning, 1 h ago
• Principled Design of Expected Improvement for Continuous Simulation Optimization · Name Convergence-Rate-Guided Algorithm Design of Expected Improvement for Continuous Simulation Optimization → Principled Design of Expected Improvement for Continuous Simulation Optimization1 h ago
• Principled Design of Expected Improvement for Continuous Simulation Optimization · Description Expected improvement (EI) based on stochastic kriging (SK) surrogate is widely used in continuous simulation optimization, but unknown heteroscedastic noise on simulation output makes three basic design choices consequential: the incumbent → Expected improvement based on stochastic kriging (SK) surrogate is widely used in continuous simulation optimization, but unknown heteroscedastic noise makes three basic design choices consequential: the incumbent to define improvement, rep1 h ago
• Read the Room Before Your Model Generates · Description Large language models (LLMs) generally rely on sampling temperature to regulate the amount of randomness in their outputs. Mainstream methods for selecting temperature typically involve fixed, heuristic global settings and context or token- → Large language models (LLMs) generally rely on sampling temperature to regulate the amount of randomness in their outputs. Mainstream methods for selecting temperature typically involve fixed, heuristic global settings and context or token-1 h ago