分享
扫一扫
超级会员免费看
UnknownBody
AI博士，最近一直follow大模型相关论文，每日会更新学术界论文的进展。
展开
专栏收录文章
- 默认排序
- 最新发布
- 最早发布
- 最多阅读
- 最少阅读
-
Learning to Retrieve via Reinforcement Learning in Embedding Space
Learning to Retrieve via Reinforcement Learning in Embedding Space 论文总结与翻译论文arXiv地址：https://arxiv.org/abs/2610.07731原创 2026-11-01 13:00:00 · 3 阅读 · 0 评论 -
Foresight-over-Graph: Reasoning Beyond Local Horizons for Knowledge Base Question Answering
> 说明：当前仅获取到论文摘要元数据，**无法拿到Introduction与Conclusion原文**，因此仅完成：文章主要内容&创新点总结、Abstract中英对照翻译；Introduction、Conclusion部分因缺少全文文本无原创 2026-11-01 12:00:00 · 2 阅读 · 0 评论 -
SquidAgent: Parallelize Wisely, Coordinate Efficiently
# SquidAgent: Parallelize Wisely, Coordinate Efficiently 论文总结与翻译> 论文信息：arXiv:2610.08647，NeurIPS 2026接收，37页（含附录）## 一、文原创 2026-11-01 10:00:00 · 66 阅读 · 0 评论 -
The Model Plants the Trigger: Answer‑Side Backdoor Attacks in Multi‑Turn Large Language Models
# The Model Plants the Trigger: Answer‑Side Backdoor Attacks in Multi‑Turn Large Language Models> Paper: arXiv:2610.077原创 2026-11-01 09:00:00 · 131 阅读 · 0 评论 -
Safeguarding LLMs via Model‑Agnostic Latent Safety Signals from Dark Knowledge 论文阅读笔记
# Safeguarding LLMs via Model‑Agnostic Latent Safety Signals from Dark Knowledge 论文阅读笔记> 论文arXiv链接：[https://arxiv.org/a原创 2026-10-31 13:00:00 · 4 阅读 · 0 评论 -
Beyond Refusal Patterns 论文总结与翻译
# Beyond Refusal Patterns 论文总结与翻译> 论文信息：arXiv:2610.07023 | Beyond Refusal Patterns: Safe‑Role Internalization for Robus原创 2026-10-31 12:00:00 · 5 阅读 · 0 评论 -
COMPASS: Finding Where Reasoning Lives in Language Models（arXiv:2610.07469）
# COMPASS: Finding Where Reasoning Lives in Language Models（arXiv:2610.07469）> 论文链接：https://arxiv.org/abs/2610.07469#原创 2026-11-01 08:00:00 · 4 阅读 · 0 评论 -
WASD: Wasserstein‑based Knowledge Distillation for Large Language Models 论文总结与翻译
# WASD: Wasserstein‑based Knowledge Distillation for Large Language Models 论文总结与翻译> 论文信息：arXiv:2610.07706，NeurIPS 2026原创 2026-11-01 07:00:00 · 4 阅读 · 0 评论 -
Distributionally Robust Mixture‑of‑Experts Training（DRMoET）论文总结与翻译
# Distributionally Robust Mixture‑of‑Experts Training（DRMoET）论文总结与翻译> 论文信息：arXiv:2610.07207，NeurIPS 2026，作者：Xin Teng, M原创 2026-10-31 08:00:00 · 87 阅读 · 0 评论 -
CoDe‑LoRA 论文阅读总结
# CoDe‑LoRA 论文阅读总结> 论文信息：CoDe‑LoRA: Mitigating the Orthogonality Dilemma in Continual Learning of LLMs via Knowledge Co原创 2026-10-31 07:00:00 · 92 阅读 · 0 评论 -
Dynamic Positional Attention Modulation 论文阅读笔记
# Dynamic Positional Attention Modulation 论文阅读笔记> 论文信息：arXiv:2610.07848，KDD 2026，标题：*Dynamic Positional Attention Modul原创 2026-10-30 07:00:00 · 72 阅读 · 0 评论 -
Illusory Pattern Perception Drives Spurious Inference in Large Language Models 论文总结与译文
# Illusory Pattern Perception Drives Spurious Inference in Large Language Models 论文总结与译文> 论文信息：arXiv:2610.07791，NeurIPS原创 2026-10-29 09:00:00 · 8 阅读 · 0 评论 -
Understanding and Enhancing Backdoor Persistency in LLM Agent Post‑Training 论文总结与翻译
# Understanding and Enhancing Backdoor Persistency in LLM Agent Post‑Training 论文总结与翻译> 论文arXiv：https://arxiv.org/abs/26原创 2026-10-29 08:00:00 · 101 阅读 · 0 评论 -
Rationale‑Guided Policy Optimization（RGPO）论文总结与翻译
# Rationale‑Guided Policy Optimization（RGPO）论文总结与翻译> 论文信息：arXiv:2610.07342｜NeurIPS 2026｜[论文仓库](https://github.com/VietH原创 2026-10-28 13:00:00 · 7 阅读 · 0 评论 -
Component and Dimension Sparsity in Transformer Refusal Mechanisms 论文总结
# Component and Dimension Sparsity in Transformer Refusal Mechanisms 论文总结> 论文信息：arXiv:2610.06903，接收于COLM 2026，作者：Vincen原创 2026-10-28 12:00:00 · 7 阅读 · 0 评论 -
MILO: Efficient Many‑shot In‑Context Learning with Block‑wise Low‑rank Compression
> 说明：arXiv摘要页面仅公开**Abstract**，未直接展示Introduction、Conclusion完整原文；PDF需要读取完整论文。当前可获取完整的只有Abstract，因此我完成：论文整体总结、创新点、Abstract中原创 2026-10-29 07:00:00 · 125 阅读 · 0 评论 -
CodeGraph: Open‑Taxonomy Knowledge Graph for Source Code with Wikidata Grounding
# CodeGraph: Open‑Taxonomy Knowledge Graph for Source Code with Wikidata Grounding> 论文arXiv链接：[https://arxiv.org/abs/26原创 2026-10-28 09:00:00 · 90 阅读 · 0 评论 -
LogicTrack: Auditing Reasoning Trajectories of Large Language Models with Formal Logic Solvers 论文总结与
# LogicTrack: Auditing Reasoning Trajectories of Large Language Models with Formal Logic Solvers 论文总结与翻译> 论文arXiv链接：htt原创 2026-10-28 08:00:00 · 104 阅读 · 0 评论 -
Abstention and Noise Filtering: Two Missing Primitives of Softmax Attention 论文阅读总结
# Abstention and Noise Filtering: Two Missing Primitives of Softmax Attention 论文阅读总结> 论文arXiv链接：[https://arxiv.org/abs/原创 2026-10-27 13:00:00 · 8 阅读 · 0 评论 -
Block‑Sparse Attention with Semantic‑Geometric Decoupled Routing（arXiv:2609.22884）论文总结与翻译
# Block‑Sparse Attention with Semantic‑Geometric Decoupled Routing（arXiv:2609.22884）论文总结与翻译> 论文链接：[https://arxiv.org/ab原创 2026-10-27 12:00:00 · 7 阅读 · 0 评论 -
Accelerating Dense LLMs via L0‑regularized Mixture‑of‑Experts 论文总结与翻译
# Accelerating Dense LLMs via L0‑regularized Mixture‑of‑Experts 论文总结与翻译> 论文arXiv链接：https://arxiv.org/abs/2609.21672##原创 2026-10-28 07:00:00 · 6 阅读 · 0 评论 -
GVPO++: Group Variance Policy Optimization for LLM Post‑Training and On‑Policy Distillation
# GVPO++: Group Variance Policy Optimization for LLM Post‑Training and On‑Policy Distillation> 论文链接：https://arxiv.org/a原创 2026-10-27 10:00:00 · 298 阅读 · 0 评论 -
RBS‑Attention 论文阅读总结
# RBS‑Attention 论文阅读总结> 论文信息：arXiv:2609.20971，RBS‑Attention: Radius‑Bounded Sparse Prefill for Long‑Context Large Langu原创 2026-10-27 09:00:00 · 93 阅读 · 0 评论 -
What Matters for Aggressive Decoding‑Time KV Eviction? Temporal Aggregation and Ranking Preservation
# What Matters for Aggressive Decoding‑Time KV Eviction? Temporal Aggregation and Ranking Preservation> arXiv:2609.0351原创 2026-10-26 15:00:00 · 9 阅读 · 0 评论 -
GrowPage: On‑Demand KV Budgeting for Efficient LLM Reasoning Serving（arXiv:2609.03494）
# GrowPage: On‑Demand KV Budgeting for Efficient LLM Reasoning Serving（arXiv:2609.03494）> 论文链接：[https://arxiv.org/abs/2原创 2026-10-26 14:00:00 · 8 阅读 · 0 评论 -
Random Attention: Rethinking KV Cache Eviction for Efficient Reasoning（arXiv:2609.03430）
# Random Attention: Rethinking KV Cache Eviction for Efficient Reasoning（arXiv:2609.03430）## 一、文章主要内容总结### 研究背景大模型在长链原创 2026-10-27 08:00:00 · 136 阅读 · 0 评论 -
SWE‑Gate 论文阅读总结
# SWE‑Gate 论文阅读总结> 论文信息：arXiv:2609.04167，SWE‑Gate: Passing Functional Tests Is Not Enough for Software Engineering Agen原创 2026-10-27 07:00:00 · 9 阅读 · 0 评论 -
Large Language Models in Resolving Contextual Knowledge Conflicts（arXiv:2609.03148）
# Large Language Models in Resolving Contextual Knowledge Conflicts（arXiv:2609.03148）> 会议：EMNLP 2026> 论文链接：https://arx原创 2026-10-26 13:00:00 · 6 阅读 · 0 评论 -
RuleMem: Active Rule Memory for Long‑Term Conversational Agents 论文总结与翻译
# RuleMem: Active Rule Memory for Long‑Term Conversational Agents 论文总结与翻译> 论文arXiv链接：https://arxiv.org/abs/2609.03915原创 2026-10-26 12:00:00 · 7 阅读 · 0 评论 -
MemoryLACE论文总结与翻译
# MemoryLACE论文总结与翻译> 论文信息：arXiv:2609.03201，MemoryLACE: Memory Lifecycle‑Aware Consolidation and Evidence Retrieval##原创 2026-10-25 16:00:00 · 9 阅读 · 0 评论 -
Representational alignment yields generalizable safety in language models
> 说明：arXiv网页摘要接口仅公开**Abstract**，**Introduction、Conclusion**正文内容不在返回的元数据中，无法直接获取原文，因此仅完成摘要原文+翻译；文章主要内容、创新点基于摘要信息整理。# Re原创 2026-10-26 11:00:00 · 110 阅读 · 0 评论 -
It‘s the Problem, Not the Path: Budget and Difficulty Confounds in LLM Reasoning Trajectories
# It's the Problem, Not the Path: Budget and Difficulty Confounds in LLM Reasoning Trajectories> 论文arXiv地址：https://arxi原创 2026-10-26 10:00:00 · 140 阅读 · 0 评论 -
FlowBalance 论文阅读笔记
# FlowBalance 论文阅读笔记> 论文信息：FlowBalance: Verifier‑Grounded Self‑Improvement from On‑Policy Reasoning Experience，arXiv:26原创 2026-10-25 15:00:00 · 7 阅读 · 0 评论 -
The Geometr\(\boldsymbol{y}\) of Ignorance: LLMs Know \(\bolds\(\boldsymbol{y}\)mbol{\(\boldsymbol{W
# The Geometr\(\boldsymbol{y}\) of Ignorance: LLMs Know \(\bolds\(\boldsymbol{y}\)mbol{\(\boldsymbol{W}\)}\)hen to Tempe原创 2026-10-25 14:00:00 · 9 阅读 · 0 评论 -
Legibility is Not Interpretability: Comparing Judged and Actual Importance in Chain‑Of‑Thought Reaso
# Legibility is Not Interpretability: Comparing Judged and Actual Importance in Chain‑Of‑Thought Reasoning> 论文信息：arXiv:原创 2026-10-24 16:00:00 · 9 阅读 · 0 评论 -
论文总结：Doesn‘t Stop Reasoning: Analysis of Spurious CoT Termination
# 论文总结：Doesn't Stop Reasoning: Analysis of Spurious CoT Termination> 论文arXiv：https://arxiv.org/abs/2609.03633> 会议：EMNL原创 2026-10-26 09:00:00 · 210 阅读 · 0 评论 -
ALRA: Adaptive Local Relational Alignment 论文总结与翻译
# ALRA: Adaptive Local Relational Alignment 论文总结与翻译> 论文信息：arXiv:2609.03355，基于Logit的自回归语言模型预训练蒸馏自适应局部关系对齐方法## 一、文章主要内容原创 2026-10-25 13:00:00 · 10 阅读 · 0 评论 -
Dream‑RSI: Recursive Self‑Improvement through Evolving Worlds 论文总结与翻译
# Dream‑RSI: Recursive Self‑Improvement through Evolving Worlds 论文总结与翻译> 论文信息：arXiv:2609.14858（v2，2026‑10‑06）> 作者：Tong原创 2026-10-25 12:00:00 · 12 阅读 · 0 评论 -
SoL‑Pi: Recursively Scaling Auto‑Research Loops for Efficient Agent Harness 论文总结与翻译
# SoL‑Pi: Recursively Scaling Auto‑Research Loops for Efficient Agent Harness 论文总结与翻译> 论文arXiv：https://arxiv.org/abs/26原创 2026-10-24 15:00:00 · 11 阅读 · 0 评论 -
论文阅读笔记：Grounded Skill Synthesis from Code at Scale for Agentic Intelligence
# 论文阅读笔记：Grounded Skill Synthesis from Code at Scale for Agentic Intelligence> arxiv：https://arxiv.org/abs/2609.05571>原创 2026-10-24 14:00:00 · 13 阅读 · 0 评论