LMC Feed

LLM & AI News·RSS·Archive

j/k navo openx expand

1.Forms of LLM-Integrated Applications from LLM-Chats to Autonomous AI Agent System(arxiv.org)

49 pts·arXiv cs.AI·2h·research

2.CPR for LLMs: Critical-Point Routing against Catastrophic Forgetting in Domain Adaptation(arxiv.org)

74 pts·arXiv cs.AI·2h·research

3.PlurVA-LLM-2026 Shared Task Track-1: Pluralistic Value Alignment in LLMs via Multilingual Fine-Tuning and Threshold Calibration(arxiv.org)

84 pts·arXiv cs.CL·2h·research

4.Claude Haiku 5.5 arrives with massive price cuts proving the AI pricing arms race is far from over(the-decoder.com)

41 pts·The Decoder·20h·release

5.Strategic Governance of AI Models in Earth Science(arxiv.org)

89 pts·arXiv cs.AI·2h·research

6.Do LLMs Learn from Rewards in Context? : Rethinking the role of reward in In-Context Reinforcement Learning(arxiv.org)

43 pts·arXiv cs.CL·2h·research

7.How Oracle turns days of work into minutes with ChatGPT and Codex(openai.com)

35 pts·OpenAI·14h·news

8.How Narrative Wrapping Affects LLM Refusal: A Cross-Language Benchmark and Defense(arxiv.org)

84 pts·arXiv cs.AI·2h·research

9.Mooncake: A KVCache-centric Disaggregated Architecture for LLM Serving(arxiv.org)

62 pts·arXiv cs.AI·2h·research

10.Beyond Imitation: A Framework and Benchmark for LLM-Assisted Peer Review(arxiv.org)

31 pts·arXiv cs.AI·2h·research

11.When Lower Reconstruction Loss Hurts: Distributionally Robust Refinement for Low-Bit LLM Quantization(arxiv.org)

68 pts·arXiv cs.AI·2h·research

12.Universal Textual Teaching for LLMs(arxiv.org)

66 pts·arXiv cs.AI·2h·research

13.Prior or Feedback? What an LLM Uses When Adapting Neural Operators(arxiv.org)

75 pts·arXiv cs.AI·2h·research

14.Grammar Concept Annotation at Scale: Deployed Fine-Tuned Small Language Models Outperform Prompted Frontier Models(arxiv.org)

37 pts·arXiv cs.AI·2h·research

15.DataVista: Diagnosing Multimodal LLMs on Data Video Understanding(arxiv.org)

77 pts·arXiv cs.AI·2h·research

16.DVD: Dynamic Vector Decoding for Efficient MLLM-based Perception(arxiv.org)

53 pts·arXiv cs.AI·2h·research

17.Rethinking Latency Denial-of-Service: Attacking the LLM Serving Framework, Not the Model(arxiv.org)

83 pts·arXiv cs.AI·2h·research

18.SparKV: Overhead-Aware KV Cache Loading for Efficient On-Device LLM Inference(arxiv.org)

58 pts·arXiv cs.AI·2h·research

19.MemCalib: Benchmarking and Optimizing Memory Use in LLM Agents(arxiv.org)

35 pts·arXiv cs.AI·2h·research

20.How Do LLMs Change Predictions Under Negation?(arxiv.org)

42 pts·arXiv cs.AI·2h·research

21.Can a System-One LLM Perform Knowledge Tracing When Few or No Learners Are Logged?(arxiv.org)

70 pts·arXiv cs.CL·2h·research

22.TokenRouter: Efficient Serving System for Token-Level LLM Routing(arxiv.org)

44 pts·arXiv cs.CL·2h·research

23.From a Prompt to Repertoires: Evolving Functional REpertoires Enable LLM Continual Learning(arxiv.org)

56 pts·arXiv cs.CL·2h·research

24.SparseDecoding: Decoding-Aware Pruning for Accurate and Efficient LLM Inference(arxiv.org)

60 pts·arXiv cs.CL·2h·research

25.WOVEN: Weaving Visual World Modeling into Multimodal LLMs(arxiv.org)

57 pts·arXiv cs.CL·2h·research

26.Are Near-Tied LLM Rankings Robust to Family-DIF-Guided Benchmark Recomposition?(arxiv.org)

81 pts·arXiv cs.CL·2h·research

27.Stochastic Rounding in Low-Precision Transformer Inference: A Variable-Precision Emulation Study of a Small GPT-2(arxiv.org)

54 pts·arXiv cs.CL·2h·research

28.Poster: A Preliminary Study of LLM Distillation Inference(arxiv.org)

42 pts·arXiv cs.LG·2h·research

29.Writing for the Reviewer: Defensive Writing in GPT Models(arxiv.org)

84 pts·arXiv cs.AI·2h·research

30.On the Clock: Towards Punctual and Productive Time-Budgeted AI Agents(arxiv.org)

52 pts·arXiv cs.AI·2h·research

30 of 500