1
Characterising AI Models for Cataloguing
探讨如何通过特征工程和评估方法，系统性地刻画AI模型在目录编目任务中的表现与局限性。
arXiv:2607.11353v1 Announce Type: cross Abstract: The creation of digital collections involves not only the digitisation of content, but also the crea…
2
How Much is Left? LLMs Linearly Encode Their Remaining Output Length
大语言模型秘密编码剩余输出长度，揭示其生成结构的可预测线性规律。
arXiv:2607.05316v1 Announce Type: cross Abstract: Large language models generate one token at a time, yet their responses show remarkably consistent l…
3
Shared Lexical Task Representations Explain Behavioral Variability In LLMs
揭秘共享词汇任务表征如何解释LLM行为变异，为理解大模型行为差异提供新理论框架
arXiv:2604.22027v2 Announce Type: replace-cross Abstract: One of the most common complaints about large language models (LLMs) is their prompt sensiti…
4
Do LLM Embedding Spaces Recover Expert Structure?
探究大语言模型嵌入空间能否复现专家知识结构，为理解模型内部表示提供前沿视角
arXiv:2606.23394v1 Announce Type: new Abstract: Pretrained text embeddings are increasingly used as representational maps, yet high category separabil…
5
LLM and Human Modes of Representation
探讨大语言模型与人类表征模式的差异，从认知科学视角剖析AI理解能力
arXiv:2606.21616v1 Announce Type: new Abstract: Much work on the cognitive foundations of AI has focussed on comparisons between the ways in which Lar…
6
Do Large Language Models Have Emotions?
挑战Anthropic关于LLM具有“功能性情感”的断言，从生物系统视角剖析情感本质，引发对AI情感能力的深度思辨。
arXiv:2606.14742v1 Announce Type: cross Abstract: Do LLMs have emotions? A recent paper from Anthropic reports finding internal representations of emo…
7
RepFusion: Leveraging Multimodal Priors for Denoising in Representation Space
多模态先验注入表示空间去噪，RepFusion实现更鲁棒的跨模态表征融合。
arXiv:2606.14700v1 Announce Type: new Abstract: Large language models (LLMs) are widely used in text-to-image (T2I) systems, but they are typically li…
8
Agreement in Representation Space for Open-Ended Self-Consistency
将自一致性从分类任务扩展到开放式生成，通过表征空间对齐解决代码合成与文本摘要的输出多样性挑战。
arXiv:2606.12003v1 Announce Type: new Abstract: Self-consistency improves LLM reasoning by sampling multiple outputs and selecting the most consistent…
9
Beyond representational alignment with brain-guided language models for robust reasoning
通过脑信号引导语言模型，挑战传统表征对齐方法，实现更鲁棒的推理能力。
arXiv:2606.11893v1 Announce Type: cross Abstract: The correspondence between large language models (LLMs) and the neural mechanisms underlying human h…
10
Representation Curriculum: Stagewise Training for Robust Ranking and Allocation
分阶段训练课程提升排序与分配任务的鲁棒性，构建渐进式表征学习策略。
arXiv:2606.09891v1 Announce Type: cross Abstract: Ranking in digital marketplaces is a dynamic exposure-allocation mechanism: displayed items shape di…
11
How Context Shapes Truth: Geometric Transformations of Statement-level Truth Representations in LLMs
上下文如何重塑LLM中的真理表征？前沿研究揭示几何级语义重构机制。
arXiv:2601.06599v2 Announce Type: replace Abstract: Large Language Models (LLMs) often encode whether a statement is true as a vector in their residua…
12
Causal Representation Learning from Network Data
提出从网络数据中学习因果表征的新方法，结合图结构与因果关系建模，为复杂网络分析提供全新视角。
arXiv:2509.01916v2 Announce Type: replace Abstract: Causal disentanglement from soft interventions is identifiable under the assumptions of linear int…
13
IDEAL: Leveraging Infinite and Dynamic Characterizations of Large Language Models for Query-focused Summarization
无限动态表征大语言模型，为查询聚焦摘要任务带来全新突破。
arXiv:2407.10486v3 Announce Type: replace Abstract: Query-focused summarization (QFS) aims to produce summaries that answer particular questions of in…
14
Interpreting Style Representations via Style-Eliciting Prompts
用大语言模型生成提示词来解释写作风格表征，破解黑箱模型的可解释性难题
arXiv:2606.05716v1 Announce Type: new Abstract: Style representation learning is a powerful tool for authorship analysis and modeling writing style, y…
15
LeCun 10亿押注的方向，全球领先视觉大模型团队早已布局
LeCun豪掷10亿押注的隐空间世界模型，早已被全球顶尖视觉大模型团队抢先布局，揭示世界状态演化的新路径。
”隐空间世界模型很难，但我们一定要做“
16
LARYBench 发布：定义具身动作表征 ImageNet，首次度量从人类视频学习的泛化表征
LARYBench （Latent Action Representation Yielding Benchmark），一个指引从大规模的视觉数据学习到通用的隐式动作表征的系统化评测基准。实验结果表明：在动作泛化和控制精度上，通用视觉模型的表现均显著优于专门为具身智能设计的动作专家模型，具身动作表征…
17
Rethinking Molecular Text Representations for LLMs: An Empirical Study
分子文本表示如何影响大语言模型性能？这项实证研究揭示关键发现，为化学与AI交叉领域提供新思路。
arXiv:2606.03057v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used for molecular tasks, but it remains unclear which…
18
MLLM-Microscope: Unlocking Hidden Structure Within Multimodal Large Language Models
创新系统MLLM-Microscope，像显微镜一样揭示多模态大语言模型内部的隐藏表征结构
arXiv:2606.00909v1 Announce Type: cross Abstract: This work presents MLLM-Microscope, a novel system designed for analyzing the hidden representations…
19
How Neural Losses Shape VAE Latents
探索VAE隐空间如何被神经损失函数塑造，揭示潜变量表征的新视角
arXiv:2606.00635v1 Announce Type: new Abstract: Modern VAEs are rarely trained with the pointwise likelihood implied by the standard $\beta$-VAE objec…
20
Internal Representation, Not Clinical Knowledge: Where Apparent LLM Triage Failures Originate
揭示LLM临床分诊失败根源：内部表征问题而非临床知识不足，输出格式影响评估结果
arXiv:2605.29889v1 Announce Type: cross Abstract: Patient-voiced clinical-triage benchmarks report high under-triage rates for consumer LLMs for const…