LMC Feed

LLM & AI News·RSS·Archive

j/k navo openx expand

1.LLMs for Survey Text Analysis - A Performance Comparison Between Humans and GPT-5 on Inductive Content Analysis(arxiv.org)

45 pts·arXiv cs.AI·2h·research

2.PepLLM: ESM-Guided Llama for Structured Protein-Peptide Binding Interface Analysis(arxiv.org)

83 pts·arXiv cs.AI·2h·research

3.Thomson Reuters Launches Its Own Frontier Model(thomsonreuters.com)

74 pts·thomsonreuters.com·4h·news

4.I Tried to Run Qwen3.8–27B on a 16GB Mac Mini with AirLLM. Here’s Exactly Where It Breaks(pub.towardsai.net)

39 pts·Towards AI·7h·infra

5.Pew study confirms sharp rise of AI-written text on the web since ChatGPT's launch(the-decoder.com)

44 pts·The Decoder·12h·research

6.llm-anthropic 0.27(simonwillison.net)

39 pts·Simon Willison·13h·tools

7.LLM4LLM: Bridging Kernel Benchmarks and Real Deployment via Closed-Loop Agentic Optimization(arxiv.org)

39 pts·arXiv cs.AI·2h·research

8.Agentic-SQL Revisited: Autonomy-Based Taxonomy and Empirical Benchmark Analysis for LLM Text-to-SQL(arxiv.org)

35 pts·arXiv cs.AI·2h·research

9.Beyond RGB: Benchmarking and Enhancing MLLMs for Hyperspectral Image Understanding via Training-Free Reasoning Framework(arxiv.org)

42 pts·arXiv cs.AI·2h·research

10.Benchmarking Composable Compression Techniques in Mixture-of-Experts LLMs(arxiv.org)

47 pts·arXiv cs.LG·2h·research

11.Lexical Perturbations Disrupt LLM Reasoning: An Empirical Study of Attention Diversion(arxiv.org)

83 pts·arXiv cs.AI·2h·research

12.BLADE: Bilevel Low-rank Augmented-Lagrangian Erasure for LLM Unlearning(arxiv.org)

35 pts·arXiv cs.AI·2h·research

13.Context-Aware Cluster Decoding: Semantic Anchor-Driven Coherence in dMLLMs(arxiv.org)

71 pts·arXiv cs.CL·2h·research

14.CALIBURN: Self-Calibrated LLM Unlearning Alignment(arxiv.org)

46 pts·arXiv cs.CL·2h·research

15.How to Orchestrate 100+ Agents With Claude Code(pub.towardsai.net)

46 pts·Towards AI·10h·tools

16.Beyond Benchmarks: LLM Evaluation with an Anthropomorphic and Lifecycle-oriented Roadmap(arxiv.org)

66 pts·arXiv cs.AI·2h·research

17.There Is No Neutral Harness: Modern LLM Leaderboards Are Manufactured by Config-Fragile Items(arxiv.org)

60 pts·arXiv cs.AI·2h·research

18.CAI-DLLM: Convergence Aware Inference for Diffusion Language Models(arxiv.org)

81 pts·arXiv cs.AI·2h·research

19.Buried in Textual Debt: Context Pruning with Visual Evidence Preservation for MLLM Agents(arxiv.org)

48 pts·arXiv cs.AI·2h·research

20.Toward Effective and Reliable LLM Agents via Dynamic Ontology(arxiv.org)

72 pts·arXiv cs.AI·2h·research

21.KAN-Robust-Bench: A Benchmark for Evaluating the Robustness of Kolmogorov-Arnold Networks(arxiv.org)

31 pts·arXiv cs.AI·2h·research

22.Anchoring Bias: A Persistent Fairness Backdoor Attack against MLLMs under Continual Learning(arxiv.org)

52 pts·arXiv cs.AI·2h·research

23.Rank Reversal in Multilingual LLM Judges: A Label-Free Double-Centering Calibrator(arxiv.org)

34 pts·arXiv cs.AI·2h·research

24.WildHandBench: A Benchmark for Handwritten Text Understanding that Challenges MLLMs and Humans(arxiv.org)

62 pts·arXiv cs.AI·2h·research

25.NetConfArena: An Executable Benchmark for LLM Agents in Closed-Loop Network Configuration(arxiv.org)

66 pts·arXiv cs.AI·2h·research

26.ATP-Bench: Towards Agentic Tool Planning for MLLM Interleaved Generation(arxiv.org)

55 pts·arXiv cs.AI·2h·research

27.Revisiting the Effectiveness of LLM Pruning for Test-Time Scaling(arxiv.org)

45 pts·arXiv cs.AI·2h·research

28.Crossing the Margin Cliff: Toward Relearn-Robust LLM Unlearning via Margin Calibration(arxiv.org)

64 pts·arXiv cs.AI·2h·research

29.Pandora's AI Model Routing Box: Efficient Allocation with Costly Value Estimation(arxiv.org)

32 pts·arXiv cs.AI·2h·research

30.Time Series Forecasting via Reasoning: A Slow-Thinking Approach with Reinforcement Fine-Tuned LLMs(arxiv.org)

34 pts·arXiv cs.AI·2h·research

30 of 500