1
A Shared Subcircuit Lets LLMs Count Down Across Tasks
大模型内部发现通用倒数机制，助你在多种任务中精准控制输出长度
arXiv:2607.12279v1 Announce Type: cross Abstract: Writing a sentence of exactly twelve words; ending a DNA sequence at the right codon; formatting an …
2
VoxENES 2026: Benchmarking Generalization of Speech Spoofing Detectors Against LLM-Era TTS and Voice Conversion
LLM时代语音合成与转换加剧深度伪造风险，这项新基准测试揭露了现有欺骗检测器的泛化短板。
arXiv:2607.11706v1 Announce Type: cross Abstract: Modern LLM-driven text-to-speech (TTS) and voice conversion (VC) systems produce synthetic speech th…
3
Contrastive Weak-to-strong Generalization
一篇探讨对比学习框架下弱到强泛化的新论文，理论分析和实验验证结合，为AI大模型泛化研究提供新视角。
arXiv:2510.07884v2 Announce Type: replace-cross Abstract: Weak-to-strong generalization provides a promising paradigm for scaling large language model…
4
When Does Continual Learning Require Learning
一作质问持续学习何时真正需要「学习」，揭示任务无关场景下模型无需更新即可泛化，引发对学习本质的再思考。
arXiv:2607.07847v1 Announce Type: new Abstract: As large language models (LLMs) become increasingly capable, the next question is how can we enable mo…
5
Cost-Effective Agent Harnesses for Abstract Reasoning and Generalization on ARC-AGI-1
低成本智能体在ARC-AGI基准上实现惊人推理性能，兼顾效率与泛化。
arXiv:2607.06764v1 Announce Type: new Abstract: Recent progress on ARC-AGI-1 from disclosed architectures has come broadly from two regimes: heavy tes…
6
20+ 构型泛化、多自由度支持，蚂蚁灵波开源新一代具身基座模型 LingBot-VLA 2.0
IT之家 7 月 8 日消息，蚂蚁集团旗下蚂蚁灵波科技今日正式官宣新一代具身基座模型 LingBot-VLA 2.0 全面开源。官方称，作为今年 1 月开源的 LingBot-VLA 1.0 的全面升级，LingBot-VLA 2.0 在构型泛化、自由度支持和落地效率等方面实现了显著提升。 IT之家…
7
SleepBand: Single-Source Domain Generalization for Sleep Staging via Physiologically Structured Spectral Modeling
不用重新训练，仅靠单源数据！新方法用生理结构化的频谱建模实现跨域睡眠分期泛化。
arXiv:2607.04851v1 Announce Type: cross Abstract: Generalizing sleep staging models to unseen datasets is challenging, and typical domain generalizati…
8
Safety Targeted Embedding Exploit via Refinement
揭露低资源语言与混合代码切换可绕过LLM安全防护，揭示模型安全泛化的关键漏洞。
arXiv:2607.01859v1 Announce Type: new Abstract: Safety training for large language models (LLMs) is conducted predominantly in English, leaving uncert…
9
Do LLMs Truly Generalize in the Molecular Domain? A Perturbation-Based Analysis
扰动分析揭示：大模型在分子领域是否真正具备泛化能力？最新研究带来关键验证。
arXiv:2607.01800v1 Announce Type: new Abstract: Large Language Models (LLMs) have recently shown promise in molecular discovery, yet a gap remains bet…
10
Uncertain but Useful: Leveraging CNN Training Variability into Data Augmentation
利用CNN训练中的不确定性作为数据增强新策略，为提升模型泛化能力提供创新思路。
arXiv:2509.05238v2 Announce Type: replace-cross Abstract: Deep learning (DL) has transformed neuroimaging by delivering state-of-the-art performance w…
11
Can Agents Generalize to the Open World? Unveiling the Fragility of Static Training in Tool Use
ICML 2026接收，揭示AI智能体在真实开放世界中泛化失败的核心原因——静态训练缺陷。
arXiv:2607.01084v1 Announce Type: new Abstract: While Large Language Model (LLM) agents demonstrate proficiency in static benchmarks, their deployment…
12
LLM-Empowered Agentic MAC Protocols: A Dynamic Stackelberg Game Approach
用大模型重塑无线网络MAC协议，以动态Stackelberg博弈提升泛化与韧性，告别DRL高成本重训。
arXiv:2510.10895v2 Announce Type: replace Abstract: Medium Access Control (MAC) protocols, essential for wireless networks, are typically manually con…
13
Food for Agile Thought 550: Make AI Boring, Everyone's a Product Manager Soon
让AI回归工具本质，人人皆产品经理的时代即将到来，本文以敏捷视角探讨技术应用新趋势。
Article URL: https://age-of-product.com/food-agile-thought-550-make-ai-boring/ Comments URL: https://news.ycombinator.com/item?id=48686564 Points: 1 #…
14
Tuning without Peeking: Provable Generalization Bounds and Robust LLM Post-Training
提出“无窥视调优”方法，为大模型后训练提供可证明的泛化界限与鲁棒性保障。
arXiv:2507.01752v4 Announce Type: replace-cross Abstract: Gradient-based optimization is the workhorse of deep learning, offering efficient and scalab…
15
How LLMs Fail and Generalize in RTL Coding for Hardware Design?
研究大语言模型在硬件RTL编码中的失败与泛化表现，揭示AI辅助硬件设计的边界与潜力。
arXiv:2606.19347v1 Announce Type: cross Abstract: Translating sequential programming priors into the parallel temporal logic of hardware design remain…
16
Connect the Dots: Training LLMs for Long-Lifecycle Agents with Cross-Domain Generalization Via Reinforcement Learning
强化学习新框架“Connect the Dots”让LLM代理实现跨域泛化与长期自学习，迈向更智能的自主决策。
arXiv:2606.20002v1 Announce Type: cross Abstract: This work presents a general framework for training large language models (LLMs) to "Connect the Dot…
17
Anti-causal domain generalization: Leveraging unlabeled data
反因果视角突破域泛化瓶颈，巧用未标注数据提升模型泛化能力，ICML 2026前沿研究
arXiv:2602.17187v2 Announce Type: replace-cross Abstract: The problem of domain generalization concerns learning predictive models that are robust to …
18
What Does the Weight Norm Control in Grokking? Logit-Scale Mediation under Cross-Entropy
揭示Grokking中权重范数如何通过交叉熵下的logit尺度中介作用控制延迟泛化，为理解神经网络泛化机制提供新视角。
arXiv:2606.18465v1 Announce Type: new Abstract: Grokking, the delayed jump from memorization to generalization, is usually tied to the weight norm: a …
19
On the Memorization Behavior of LLMs in Generative Recommendation: Observations, Implications, and Training Strategies
探究LLM在生成式推荐中的记忆机制，揭示其对推荐系统泛化能力的影响与优化训练策略
arXiv:2606.17276v1 Announce Type: cross Abstract: Generative recommendation (GR) has emerged as a promising direction for recommender systems. Recentl…
20
Multimodal LLM-Empowered Re-Ranking for Generalizable Person Re-Identification
多模态大语言模型如何提升行人重识别的泛化能力？本文提出全新重排序框架，为计算机视觉领域带来突破性思路。
arXiv:2606.16161v1 Announce Type: new Abstract: Domain Generalizable (DG) person re-identification (Re-ID) has attracted growing research interest due…