1
OpenAI 推出金融服务版 ChatGPT：集成 GPT-6 Astra 内置金融数据与细粒度引用，支持估值模型与研究报告
IT之家 9 月 11 日消息，OpenAI 于当地时间 9 月 10 日宣布推出 ChatGPT for Financial Services。 这是一款面向金融服务团队的定制化 ChatGPT 服务，结合内置金融数据与 GPT-6 Astra 推理能力，旨在帮助金融团队开展研究、财务建模并制作定…
2
Reinforcing Multi-Turn Reasoning in LLM Agents via Fine-Grained Reward Structure and Credit Assignment
多轮推理强化学习新方案，细粒度奖励结构直击信用分配难题，提升LLM代理决策可靠性。
arXiv:2505.11821v3 Announce Type: replace Abstract: Reinforcement Learning (RL) approaches have been wildly used to enhance the reasoning capabilities…
3
MR-IQA-2: Faithful Image Quality Reflection via Fine-Grained Credit Assignment
提出MR-IQA-2，用细粒度信用分配让多模态大模型在图像质量评估中的推理更忠实。
arXiv:2608.18579v1 Announce Type: cross Abstract: Multimodal large language models (MLLMs) have shown strong potential for image quality assessment (I…
4
FiRE: Enhancing MLLMs with Fine-Grained Context Learning for Complex Image Retrieval
把多模态大模型调教成复杂图像检索专家，FiRE用细粒度上下文学习突破通用检索瓶颈，值得关注。
arXiv:2607.27959v1 Announce Type: new Abstract: Due to their strong generalizable multimodal processing and reasoning capabilities, Multimodal Large L…
5
Ask HN: How do you audit your app for compliance?
Permit.io 让你轻松管理应用内细粒度权限与审计日志，精准追踪谁在何时拥有管理员权限，助力 SOC2/ISO 27001 合规审计。
Compliance software like Vanta, Drata and similar only read 3rd party APIs (AWS, Github, Okta etc.) but cannot automatically audit your app that actua…
6
Detecting LLM-Generated Tokens in Human--LLM Coauthored Text
精准定位人机协作文本中AI生成的词元，突破文档级分类局限。
arXiv:2607.21458v1 Announce Type: new Abstract: The rise of human-AI collaborative writing has created a growing need for fine-grained detection metho…
7
Is "Knowing It's Malicious Enough?" Evaluating LLMs for Fine-Grained Malware Behavior Auditing
探讨大语言模型在恶意软件行为审计中的不足：仅知“是否恶意”远远不够，细粒度分析才是关键。
arXiv:2509.14335v2 Announce Type: replace-cross Abstract: Automated malware classifiers achieve strong detection performance, but auditing requires mo…
8
Can We Break LLMs Out of Self-Loops? Fine-Grained Reasoning Control with Activation Steering
用激活引导打破大模型推理死循环，实现细粒度推理控制，为LLM可解释性提供新思路。
arXiv:2607.18100v1 Announce Type: new Abstract: Extended reasoning has become standard for frontier Large Language Models (LLMs), yet the trajectories…
9
GMoT: Gated Motion-Aware Tokenization for Fine-Grained Micro-Gesture Video Reasoning with Multimodal LLMs
多模态大模型新突破，门控运动感知标记化精准分析微手势视频推理，已被顶级会议ACM MM 2026收录。
arXiv:2607.16322v1 Announce Type: cross Abstract: Micro-gesture recognition demands the detection of fleeting, spatially localized movements that are …
10
AeroRAG: Structured Multimodal Retrieval-Augmented LLM for Fine-Grained Aerial Visual Reasoning
新型多模态检索增强框架让大模型精准理解航拍图像细节，解决细粒度视觉推理难题。
arXiv:2604.17889v2 Announce Type: replace Abstract: Despite recent progress in multimodal large language models (MLLMs), reliable visual question answ…
11
BVS: Bayesian Visual Search with Multimodal Large Language Model for Fine-grained Perception
贝叶斯方法加持多模态大模型，破解细粒度视觉搜索难题，ICML 2026前沿研究。
arXiv:2607.03184v1 Announce Type: new Abstract: While Multimodal Large Language Models (MLLMs) demonstrate impressive general capabilities, they strug…
12
SEPS: Semantic-enhanced Patch Slimming Framework for fine-grained cross-modal alignment
一张图胜过千言万语，但更聪明的做法是只保留最关键的部分——看SEPS如何给视觉模型“瘦身”还能对齐得更准。
arXiv:2511.01390v2 Announce Type: replace-cross Abstract: Fine-grained cross-modal alignment aims to establish precise local correspondences between v…
13
Dataset Construction for Training LLM to Learn Analog Circuit Knowledge
让大模型学会模拟电路知识，从教科书分解细粒度节点构建高质量训练集。
arXiv:2508.10409v3 Announce Type: replace-cross Abstract: This paper constructs a textual dataset for training large language models (LLMs) to learn a…
14
Reliability-Prioritized Fine-Grained Generation in Multimodal Large
多模态大模型新方法：可靠性优先的细粒度生成，平衡质量与可信度。
arXiv:2606.29573v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) are increasingly expected to generate fine-grained descriptio…
15
TruEye: Fine-Grained Detection of AI-Generated Human Subjects in Images
细粒度检测AI生成人体图像，从面部到肢体细节精准识别，为图像真实性鉴别提供新方案。
arXiv:2606.27505v1 Announce Type: new Abstract: AI generated images are proliferating across the Internet. While some are used for entertainment, othe…
16
DiCoBench: Benchmarking Multi-Image Fine-Grained Perception via Differential and Commonality Visual Cues
新基准DiCoBench专攻多图像细粒度感知，用差异与共性视觉线索考验模型隐含理解力。
arXiv:2606.26602v1 Announce Type: new Abstract: Recent advancements in Multimodal Large Language Models (MLLMs) have demonstrated impressive fine-grai…
17
V-Zero: Answer-Label-Free On-Policy Distillation with Contrastive Evidence Gating for Fine-Grained Visual Reasoning
不靠标准答案也能蒸馏？对比证据门控加持，让细粒度视觉推理在无标签场景下自举优化，高效又亮眼。
arXiv:2606.25319v1 Announce Type: new Abstract: Fine-grained visual reasoning requires multimodal large language models (MLLMs) to identify task-relev…
18
Distribution Preference Optimization: A Fine-grained Perspective for LLM Unlearning
从分布偏好角度切入，提出细粒度优化方法解决大模型遗忘问题，视角新颖。
arXiv:2510.04773v2 Announce Type: replace-cross Abstract: As Large Language Models (LLMs) demonstrate remarkable capabilities learned from vast corpor…
19
Fine-grained Human Motion Understanding with Language Models
用语言模型实现人体运动的细粒度理解，开启人机交互新篇章。
arXiv:2606.20888v1 Announce Type: new Abstract: In this work, we propose \methodname, an LLM-based model for fine-grained human motion understanding t…
20
LOCUS: Local Visual Cue Search for Enhancing Fine-Grained Perception in Multimodal Large Language Models
新方法LOCUS通过局部视觉线索搜索，大幅提升多模态大模型对图像细节的感知能力
arXiv:2606.16586v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) remain unreliable on fine-grained visual perception, even whe…