Open Source
What's New
- Show HN: Compile the same source for GPUs and CPUs
- When Objectives and Evaluators Disagree: Evaluating Transfer for Post-hoc Demographic Framing…
- The FrontierOR Challenge: Agentic Algorithm Design for Operations Research
- SPACE: Source-free Proxy Anchor Concept Erasure for MLLMs
- Planning Width Is Hard to Approximate Even Given the Unique Optimal Plan
- QVAC Genesis III: A Large-Scale, High-Quality Open Synthetic STEM Corpus for Efficient Language…
- DAST: A VLM-LLM Framework for Cross-Interface Anomaly Detection in O-RAN
- Bridging vision-language reasoning and learned control for legged navigation in the wild
- AI GameStore: Scalable, Open-Ended Evaluation of Machine General Intelligence with Human Games
- OpenTME: An Open Dataset of AI-powered H&E Tumor Microenvironment Profiles from TCGA
- xAppGen: LLM-driven Natural Language Programming for Agile xApp Development
- Near-Quadratic Sample Compression for All VC Classes
- Measuring Hallucination in Large Language Models for Cyber Threat Intelligence: An Exploratory Study
- Flow Matching from Non-Gaussian Sources: A Theory of Efficient Sampling
- MemMend: A Selective Revision Framework for Memory Question Answering
- Validation-driven Deployment of LLM Inference Platforms for Agentic Workloads
- Controlling the Humanoid Robot H1-2 With a Simulated Biologically Plausible Network
- Energy estimates of open-weight large language models across stated food weights: a dose-response…
- The Effectiveness and Durability of Pretraining Data Filtering in Protein Language Models
- The Obsolescence of High-Level Code: Agentic Generation from Semantic Artifacts
- OpenKAGE: Open-Ended Lifelong Learning in the Open World via Knowledge-Sharing Agent-Group Evolution
- FutureBench: A Renewable Framework for Evaluating Knowledge-Context Conflict in LLMs
- Language Models Make New Research Sound Old
- Generative AI in Software Testing: Practitioners' Perspectives on the Benefits, Challenges…
- Gaussian Primitive Fusion for Any-Resolution Multimodal Images
- Probing agent overeagerness in realistic settings with continuation audits
- How Path Integral Diffusion Decides a Finite Spin Glass
- Movie2Game-Bench: Holistic Evaluation of Film-to-Game Adaptation Beyond Playability
- Rumble-2-Flash: an open 0.5B speech model for 40+ languages
- OpenFrontiers: A Collection of Open Research Problems and a Benchmark for Scientific Rediscovery
- The Economics of AI Foundation Models: Openness, Competition, and Governance
- Do LLMs Understand Network Traces? A Comparative Study of Reasoning over Raw and Filtered Traffic…
- Context Has a Price: Adding and Removing Context for LLM Coding Agents under Prefix Caching
- A Hybrid Exact-Heuristic Solver for the Integrated Passenger and Parcel Transportation Problem
- Values Shape What Self-Improving Coding Agents Build
- Process Advantage Signal Shaping: Advantage Construction for Process-Supervised Reinforcement…
- Long-Context Generation Is a Sampling Problem (When You Turn Up the Heat)
- FVScore: Specification-Driven Neuro-Symbolic Video Evaluation
- Verifying Agents in Rubric-Graded Environments
- AutoE2E: Don't speak - Language free end-to-end autonomy A Real-Time Driving Model for L2++ ADAS…

