LMC Feed

LLM & AI News·RSS·Archive

j/k navo openx expand

1.Claude Mythos reportedly solves OpenAI's landmark Erdős problem with a "cute, simple proof"(the-decoder.com)

74 pts·The Decoder·3h·news

2.Fine-Tuning and Serving Gemma 4 31B on Google Cloud TPU: A Technical Comparison with GPU Baselines(arxiv.org)

49 pts·arXiv cs.AI·17h·research

3.SoK: A Comprehensive Security Analysis of Jailbreak Resilience in GPT and DeepSeek Models(arxiv.org)

58 pts·arXiv cs.AI·17h·research

4.SafeGPT: Preventing Data Leakage and Unethical Outputs in Enterprise LLM Use(arxiv.org)

44 pts·arXiv cs.AI·17h·research

5.Red-Teaming Claude Opus and ChatGPT-based Security Advisors for Trusted Execution Environments(arxiv.org)

80 pts·arXiv cs.AI·17h·research

6.PolyGnosis 2.0: Enhancing LLM Reasoning via Agentic Harness Engineering for Polymarket and OSINT Insight Extraction(arxiv.org)

78 pts·arXiv cs.CL·17h·research

7.Safety-Oriented Routing Analysis of Mixtral MoE Under Benign and Harmful Prompts(arxiv.org)

39 pts·arXiv cs.AI·17h·research

8.PANDO: Efficient Multimodal AI Agents via Online Skill Distillation(arxiv.org)

53 pts·arXiv cs.AI·17h·research

9.IndexMem: Learned KV-Cache Eviction with Latent Memory for Long-Context LLM Inference(arxiv.org)

38 pts·arXiv cs.AI·17h·research

10.The Growing Pains of Frontier Models: When Leaderboards Stop Separating and What to Measure Next(arxiv.org)

82 pts·arXiv cs.AI·17h·research

11.RouteScan: A Non-Intrusive Approach to Auditing MoE LLMs Safety via Expert Routing Telemetry(arxiv.org)

89 pts·arXiv cs.CL·17h·research

12.Reading, Not Thinking: Understanding and Bridging the Modality Gap When Text Becomes Pixels in Multimodal LLMs(arxiv.org)

54 pts·arXiv cs.CL·17h·research

13.RepetitionCurse: Measuring and Understanding Router Imbalance in Mixture-of-Experts LLMs under DoS Stress(arxiv.org)

65 pts·arXiv cs.LG·17h·research

14.MEMOR-E: In-Context and Fine-Tuned LLM Personalization for Alzheimer's Assistive Robotics(arxiv.org)

77 pts·arXiv cs.AI·17h·research

15.Is GPT-4o mini Blinded by its Own Safety Filters? Exposing the Multimodal-to-Unimodal Bottleneck in Hate Speech Detection(arxiv.org)

72 pts·arXiv cs.LG·17h·research

16.Miller-Index-Based Latent Crystallographic Fracture Plane Reasoning and generation with Vision-Language Models(arxiv.org)

41 pts·arXiv cs.LG·17h·research

17.Authority Signals in Claude AI Health Citations: A Descriptive Analysis Using the Authority Signals Framework(arxiv.org)

87 pts·arXiv cs.AI·17h·research

18.A Two-Dimensional Framework for AI Agent Design Patterns: Cognitive Function and Execution Topology(arxiv.org)

85 pts·arXiv cs.AI·17h·research

19.LGMT: Logic-Grounded Metamorphic Testing for Evaluating the Reasoning Reliability of LLMs(arxiv.org)

38 pts·arXiv cs.AI·17h·research

20.When Correct Beliefs Collapse: Epistemic Resilience of LLMs under Clinical Pressure(arxiv.org)

34 pts·arXiv cs.AI·17h·research

21.Fuzzy, Neutrosophic, and Uncertain Graph Theory: Properties and Applications(arxiv.org)

67 pts·arXiv cs.AI·17h·research

22.When Does Multi-Agent RL Improve LLM Workflows? Workflow, Scale, and Policy-Sharing Tradeoffs(arxiv.org)

78 pts·arXiv cs.AI·17h·research

23.GlobalDentBench: A Multinational Benchmark for Evaluating LLM Clinical Reasoning in Dentistry with Expert Calibration(arxiv.org)

57 pts·arXiv cs.AI·17h·research

24.Trust but Verify: Prover-Verifier Deliberation for Selective LLM Prediction(arxiv.org)

75 pts·arXiv cs.AI·17h·research

25.FrontierOR: Benchmarking LLMs' Capacity for Efficient Algorithm Design in Large-Scale Optimization(arxiv.org)

86 pts·arXiv cs.AI·17h·research

26.Towards end-to-end LLM-based censoring-aware survival analysis(arxiv.org)

55 pts·arXiv cs.AI·17h·research

27.Check Your LLM's Secret Dictionary! Five Lines of Code Reveal What Your LLM Learned (Including What It Shouldn't Have)(arxiv.org)

81 pts·arXiv cs.AI·17h·research

28.Truthful Online Preference Aggregation for LLM Fine-Tuning in Mobile Crowdsourcing(arxiv.org)

85 pts·arXiv cs.AI·17h·research

29.When the Manual Lies: A Realistic Benchmark to Evaluate MCP Poisoning Attacks for LLM Agents(arxiv.org)

80 pts·arXiv cs.AI·17h·research

30.ChaosBench-Logic v2: Evaluating LLM Logical Reasoning over Dynamical Systems at Scale(arxiv.org)

81 pts·arXiv cs.AI·17h·research

30 of 500