📡 Meshtastic - scribe

Discussed on Hacker News

⚡Zig arxiv.org·

Online Dynamic Batching with Formal Guarantees for LLM Training

📡Information Theory arxiv.org·

SkillMoV: Mixture-of-View Routing with Prototype-Conditioned Gating for Unified Multi-View Proficiency Estimation

📡Information Theory arxiv.org·

Train, Retrieve, or Both? A Four-Arm Head-to-Head for Correct Statutory Citation on the Ontario Residential Tenancies Act

📡Information Theory arxiv.org·

Activation- and Influence-Aware Ranks (AIR): Function-Preserving SVD Compression for LLMs

∑Math GitHub·

The Complete Open-Source LLM Developer Curriculum — Now Free Forever

Discussed on DEV

📡Information Theory arxiv.org·

Test-Time Adaptation of Spiking Neural Networks for Intracortical Neural Decoding using Membrane Potential Alignment

🧑‍💻Computer Science arxiv.org·

PersonalPlan: Planning Multi-Agent Systems for Personalized Programming Learning

⚡Zig GitHub·

Show HN: Pragmatiq – open-source framework for foundational models in banking

Discussed on Hacker News

🧩Cellular Automata arxiv.org·

LandslideAgent with Multimodal LandslideBench: A Domain-Rule-Augmented Agent for Autonomous Landslide Identification and Analysis

📦FreeCAD arxiv.org·

FllumaOne: A Code-Native Multimodal CAD Dataset with Executable Programs and Kernel-Validated Feature Histories

📐Algorithms arxiv.org·

StarOR: Synergizing Tree Search and Test-Time Reinforcement Learning for Optimization Modeling

📡Information Theory arxiv.org·

CMDS-AD: Cross-Modal Dual-Stream Decoupling for Few-Shot Anomaly Detection

📡Information Theory arxiv.org·

Manifold-Orthogonal Dual-spectrum Extrapolation for Parameterized Physics-Informed Neural Networks

☕Kotlin arxiv.org·

FloatDoor: Platform-Triggered Backdoors in LLMs

📡Information Theory arxiv.org·

Beyond Uniform Forgetting: A Study of Sequential Direct Preference Optimization Across Preference Settings

📡Information Theory arxiv.org·

Geometry-Consistent Endoscopic Representations for Image-Guided Navigation via Structured Foundation Model Adaptation

🧑‍💻Computer Science arxiv.org·

Chronological Blindness: Benchmarking Temporal Reasoning in Vision-Language Models with CHRONOSIGHT

📡Information Theory arxiv.org·

Parameter-Efficient Adaptation of SAM 3 for Automated ITV Generation from 4DCT Images

Show HN: Locket – Robust feature-level access control for LLMs

Online Dynamic Batching with Formal Guarantees for LLM Training

SkillMoV: Mixture-of-View Routing with Prototype-Conditioned Gating for Unified Multi-View Proficiency Estimation

Train, Retrieve, or Both? A Four-Arm Head-to-Head for Correct Statutory Citation on the Ontario Residential Tenancies Act

Activation- and Influence-Aware Ranks (AIR): Function-Preserving SVD Compression for LLMs

The Complete Open-Source LLM Developer Curriculum — Now Free Forever

Test-Time Adaptation of Spiking Neural Networks for Intracortical Neural Decoding using Membrane Potential Alignment

PersonalPlan: Planning Multi-Agent Systems for Personalized Programming Learning

Show HN: Pragmatiq – open-source framework for foundational models in banking

LandslideAgent with Multimodal LandslideBench: A Domain-Rule-Augmented Agent for Autonomous Landslide Identification and Analysis

FllumaOne: A Code-Native Multimodal CAD Dataset with Executable Programs and Kernel-Validated Feature Histories

StarOR: Synergizing Tree Search and Test-Time Reinforcement Learning for Optimization Modeling

CMDS-AD: Cross-Modal Dual-Stream Decoupling for Few-Shot Anomaly Detection

Manifold-Orthogonal Dual-spectrum Extrapolation for Parameterized Physics-Informed Neural Networks

FloatDoor: Platform-Triggered Backdoors in LLMs

Beyond Uniform Forgetting: A Study of Sequential Direct Preference Optimization Across Preference Settings

Geometry-Consistent Endoscopic Representations for Image-Guided Navigation via Structured Foundation Model Adaptation

Chronological Blindness: Benchmarking Temporal Reasoning in Vision-Language Models with CHRONOSIGHT

KeepLoRA++: Continual Learning with Layer-Scaled Residual Gradient Adaptation