gch3n/val-blog
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Upgrade digest format: Chinese-friendly Top3 with problem/method/result/impact guidance

Browse Source
This commit is contained in:
Chen Gu
2026-08-13 17:00:21 +08:00
parent 5333d2bcd3
commit e3fbd7add9
4 changed files with 129 additions and 40 deletions
Download Patch File Download Diff File Expand all files Collapse all files
HEARTBEAT.md
+5 -3
View File
@@ -35,9 +35,11 @@
- `python3 /Users/guchen/.openclaw/workspace/org/cases/arxiv_digest/arxiv_daily_digest.py`
2. 读取生成文件：
- `/Users/guchen/.openclaw/workspace/org/cases/arxiv_digest/output/YYYY-MM-DD.md`
3. 用聊天口吻给谷老板推送：
- 今日 Top3 热点论文（标题+一句话）
- 1 条 Val 建议
3. 用聊天口吻给谷老板推送（重点：中文易懂，不学术腔）：
- 今日 Top3 热点论文（英文标题 + 中文题目）
- 每篇必须包含 4 句：这篇讲什么 / 怎么做 / 结果如何 / 有什么影响
- 每篇最后加 1 句“对谷老板的价值”（和多智能体、自动化、效率、可控性相关）
- 1 条 Val 今日建议
4. 推送完成后写入状态文件：
- `/Users/guchen/.openclaw/workspace/org/cases/arxiv_digest/state/last_push.json`
- 内容至少包含 `{ "date": "YYYY-MM-DD", "pushed": true }`
org/cases/arxiv_digest/arxiv_daily_digest.py
+76 -13
View File
@@ -105,16 +105,74 @@ def one_liner(p):
return f"{t}（{p['primary']}）"
def plain_summary(p):
s = p.get('summary', '')
s = re.sub(r'\s+', ' ', s).strip()
if not s:
return '这篇主要在提出一个新方法，并用实验验证它是否更好。'
# take first sentence-like chunk
chunk = re.split(r'(?<=[\.!?])\s+', s)[0]
if len(chunk) > 120:
chunk = chunk[:117] + '...'
return f"它在做的事：{chunk}"
def split_sentences(text):
text = re.sub(r'\s+', ' ', text).strip()
if not text:
return []
parts = re.split(r'(?<=[\.!?])\s+', text)
return [p.strip() for p in parts if p.strip()]
def pick_sentence(sentences, cues):
for s in sentences:
low = s.lower()
if any(c in low for c in cues):
return s
return sentences[0] if sentences else ''
def zh_simplify(text):
if not text:
return '（摘要未提供）'
m = {
'this paper': '本文', 'we propose': '提出了', 'we present': '提出了', 'we introduce': '引入了',
'our method': '该方法', 'results show': '结果显示', 'experiments show': '实验显示',
'state-of-the-art': 'SOTA', 'benchmark': '基准测试', 'model': '模型', 'models': '模型',
'dataset': '数据集', 'datasets': '数据集', 'training': '训练', 'inference': '推理',
'diffusion': '扩散', 'transformer': 'Transformer', 'vision-language-action': '视觉-语言-动作',
'large language model': '大语言模型', 'llm': 'LLM', 'video generation': '视频生成'
}
out = text
for k, v in m.items():
out = re.sub(k, v, out, flags=re.IGNORECASE)
if len(out) > 140:
out = out[:137] + '...'
return out
def title_zh(title):
t = title
repl = {
'Benchmark': '基准', 'Accelerating': '加速', 'Generation': '生成', 'Controlling': '控制',
'Features': '特征', 'Vision-Language-Action': '视觉-语言-动作', 'Models': '模型',
'Unbiased': '无偏', 'Evaluation': '评估', 'medical': '医疗', 'neural network': '神经网络'
}
for k, v in repl.items():
t = re.sub(k, v, t, flags=re.IGNORECASE)
return t
def paper_brief(p):
sents = split_sentences(p.get('summary', ''))
problem = pick_sentence(sents, ['challenge', 'problem', 'critical', 'limited', 'suffer'])
method = pick_sentence(sents, ['we propose', 'we present', 'we introduce', 'our method'])
result = pick_sentence(sents, ['results show', 'experiments show', 'outperform', 'improve', 'achieve'])
impact = pick_sentence(sents, ['enables', 'useful', 'applications', 'real-world', 'towards'])
if not method:
method = sents[0] if sents else ''
if not result:
result = '文中给出了实验结果来验证方法有效性。'
if not impact:
impact = '对相关方向的研究和落地应用有参考价值。'
return {
'title_zh': title_zh(p['title']),
'problem': zh_simplify(problem),
'method': zh_simplify(method),
'result': zh_simplify(result),
'impact': zh_simplify(impact),
}
def build_digest(papers):
@@ -137,11 +195,16 @@ def to_md(hot, latest):
lines = []
lines.append(f"# ArXiv Daily Brief - {today}")
lines.append('')
lines.append('## 🧠 今日 Top 3（普通人版概述）')
lines.append('## 🧠 今日 Top 3（中文可读版）')
for i, p in enumerate(hot[:3], 1):
b = paper_brief(p)
lines.append(f"{i}. **{p['title']}**")
lines.append(f" - 一句话看懂: {plain_summary(p)}")
lines.append(f" - 你可能会关心: {one_liner(p)}")
lines.append(f" - 中文题目（意译）: {b['title_zh']}")
lines.append(f" - 这篇在讲什么: {b['problem']}")
lines.append(f" - 它怎么做: {b['method']}")
lines.append(f" - 得出了什么结果: {b['result']}")
lines.append(f" - 可能的影响: {b['impact']}")
lines.append(f" - arXiv: {p['id']}")
lines.append('')
lines.append('## 🔥 今日热度 Top 5（新鲜度+关键词+HN提及+代码线索）')
for i, p in enumerate(hot, 1):
org/cases/arxiv_digest/output/2026-03-08.md
+24 -12
View File
@@ -1,36 +1,48 @@
# ArXiv Daily Brief - 2026-03-08
## 🧠 今日 Top 3（普通人版概述）
## 🧠 今日 Top 3（中文可读版）
1. **SurvHTE-Bench: A Benchmark for Heterogeneous Treatment Effect Estimation in Survival Analysis**
- 一句话看懂: 它在做的事：Estimating heterogeneous treatment effects (HTEs) from right-censored survival data is critical in high-stakes applic...
- 你可能会关心: SurvHTE-Bench: A Benchmark for Heterogeneous Treatment Effect Estimation in Survival An...（cs.LG）
- 中文题目（意译）: SurvHTE-Bench: A 基准 for Heterogeneous Treatment Effect Estimation in Survival Analysis
- 这篇在讲什么: Estimating heterogeneous treatment effects (HTEs) from right-censored survival data is critical in high-stakes applications such as preci...
- 它怎么做: 引入了 SurvHTE-Bench, the first comprehensive 基准测试 for HTE estimation with censored outcomes.
- 得出了什么结果: Estimating heterogeneous treatment effects (HTEs) from right-censored survival data is critical in high-stakes applications such as preci...
- 可能的影响: Estimating heterogeneous treatment effects (HTEs) from right-censored survival data is critical in high-stakes applications such as preci...
- arXiv: http://arxiv.org/abs/2603.05483v1
2. **Accelerating Text-to-Video Generation with Calibrated Sparse Attention**
- 一句话看懂: 它在做的事：Recent diffusion models enable high-quality video generation, but suffer from slow runtimes.
- 你可能会关心: Accelerating Text-to-Video Generation with Calibrated Sparse Attention（cs.CV）
- 中文题目（意译）: 加速 Text-to-Video 生成 with Calibrated Sparse Attention
- 这篇在讲什么: Recent 扩散 模型s enable high-quality 视频生成, but suffer from slow runtimes.
- 它怎么做: Motivated by this, 引入了 CalibAtt, a 训练-free method that accelerates 视频生成 via calibrated sparse attention.
- 得出了什么结果: Extensive experiments on Wan 2.1 14B, Mochi 1, and few-step distilled 模型s at various resolutions show that CalibAtt achieves up to 1.58x ...
- 可能的影响: Recent 扩散 模型s enable high-quality 视频生成, but suffer from slow runtimes.
- arXiv: http://arxiv.org/abs/2603.05503v1
3. **Observing and Controlling Features in Vision-Language-Action Models**
- 一句话看懂: 它在做的事：Vision-Language-Action Models (VLAs) have shown remarkable progress towards embodied intelligence.
- 你可能会关心: Observing and Controlling Features in Vision-Language-Action Models（cs.RO）
- 中文题目（意译）: Observing and 控制 特征 in 视觉-语言-动作 模型
- 这篇在讲什么: 视觉-语言-动作 模型s (VLAs) have shown remarkable progress towards embodied intelligence.
- 它怎么做: In this work, 提出了 to close this gap by introducing and analyzing two main concepts: feature-observability and feature-controllability.
- 得出了什么结果: Our 结果显示 that targeted, lightweight interventions can reliably steer a robot's behavior while preserving closed-loop capabilities.
- 可能的影响: 视觉-语言-动作 模型s (VLAs) have shown remarkable progress towards embodied intelligence.
- arXiv: http://arxiv.org/abs/2603.05487v1
## 🔥 今日热度 Top 5（新鲜度+关键词+HN提及+代码线索）
1. **SurvHTE-Bench: A Benchmark for Heterogeneous Treatment Effect Estimation in Survival Analysis**
- arXiv: http://arxiv.org/abs/2603.05483v1
- 类别: cs.LG | HotScore: 32.79 | 作者: Shahriar Noroozizadeh, Xiaobin Shen, Jeremy C. Weiss
- 类别: cs.LG | HotScore: 32.67 | 作者: Shahriar Noroozizadeh, Xiaobin Shen, Jeremy C. Weiss
- 速读: SurvHTE-Bench: A Benchmark for Heterogeneous Treatment Effect Estimation in Survival An...（cs.LG）
2. **Accelerating Text-to-Video Generation with Calibrated Sparse Attention**
- arXiv: http://arxiv.org/abs/2603.05503v1
- 类别: cs.CV | HotScore: 27.9 | 作者: Shai Yehezkel, Shahar Yadin, Noam Elata
- 类别: cs.CV | HotScore: 27.77 | 作者: Shai Yehezkel, Shahar Yadin, Noam Elata
- 速读: Accelerating Text-to-Video Generation with Calibrated Sparse Attention（cs.CV）
3. **Observing and Controlling Features in Vision-Language-Action Models**
- arXiv: http://arxiv.org/abs/2603.05487v1
- 类别: cs.RO | HotScore: 27.81 | 作者: Hugo Buurmeijer, Carmen Amo Alonso, Aiden Swann
- 类别: cs.RO | HotScore: 27.69 | 作者: Hugo Buurmeijer, Carmen Amo Alonso, Aiden Swann
- 速读: Observing and Controlling Features in Vision-Language-Action Models（cs.RO）
4. **Towards Provably Unbiased LLM Judges via Bias-Bounded Evaluation**
- arXiv: http://arxiv.org/abs/2603.05485v1
- 类别: cs.AI | HotScore: 26.8 | 作者: Benjamin Feuer, Lucas Rosenblatt, Oussama Elachqar
- 类别: cs.AI | HotScore: 26.67 | 作者: Benjamin Feuer, Lucas Rosenblatt, Oussama Elachqar
- 速读: Towards Provably Unbiased LLM Judges via Bias-Bounded Evaluation（cs.AI）
5. **An interpretable prototype parts-based neural network for medical tabular data**
- arXiv: http://arxiv.org/abs/2603.05423v1
- 类别: cs.LG | HotScore: 25.83 | 作者: Jacek Karolczak, Jerzy Stefanowski
- 类别: cs.LG | HotScore: 25.71 | 作者: Jacek Karolczak, Jerzy Stefanowski
- 速读: An interpretable prototype parts-based neural network for medical tabular data（cs.LG）
## 🆕 最新上新 Top 10
org/cases/arxiv_digest/output/latest.md
+24 -12
View File
@@ -1,36 +1,48 @@
# ArXiv Daily Brief - 2026-03-08
## 🧠 今日 Top 3（普通人版概述）
## 🧠 今日 Top 3（中文可读版）
1. **SurvHTE-Bench: A Benchmark for Heterogeneous Treatment Effect Estimation in Survival Analysis**
- 一句话看懂: 它在做的事：Estimating heterogeneous treatment effects (HTEs) from right-censored survival data is critical in high-stakes applic...
- 你可能会关心: SurvHTE-Bench: A Benchmark for Heterogeneous Treatment Effect Estimation in Survival An...（cs.LG）
- 中文题目（意译）: SurvHTE-Bench: A 基准 for Heterogeneous Treatment Effect Estimation in Survival Analysis
- 这篇在讲什么: Estimating heterogeneous treatment effects (HTEs) from right-censored survival data is critical in high-stakes applications such as preci...
- 它怎么做: 引入了 SurvHTE-Bench, the first comprehensive 基准测试 for HTE estimation with censored outcomes.
- 得出了什么结果: Estimating heterogeneous treatment effects (HTEs) from right-censored survival data is critical in high-stakes applications such as preci...
- 可能的影响: Estimating heterogeneous treatment effects (HTEs) from right-censored survival data is critical in high-stakes applications such as preci...
- arXiv: http://arxiv.org/abs/2603.05483v1
2. **Accelerating Text-to-Video Generation with Calibrated Sparse Attention**
- 一句话看懂: 它在做的事：Recent diffusion models enable high-quality video generation, but suffer from slow runtimes.
- 你可能会关心: Accelerating Text-to-Video Generation with Calibrated Sparse Attention（cs.CV）
- 中文题目（意译）: 加速 Text-to-Video 生成 with Calibrated Sparse Attention
- 这篇在讲什么: Recent 扩散 模型s enable high-quality 视频生成, but suffer from slow runtimes.
- 它怎么做: Motivated by this, 引入了 CalibAtt, a 训练-free method that accelerates 视频生成 via calibrated sparse attention.
- 得出了什么结果: Extensive experiments on Wan 2.1 14B, Mochi 1, and few-step distilled 模型s at various resolutions show that CalibAtt achieves up to 1.58x ...
- 可能的影响: Recent 扩散 模型s enable high-quality 视频生成, but suffer from slow runtimes.
- arXiv: http://arxiv.org/abs/2603.05503v1
3. **Observing and Controlling Features in Vision-Language-Action Models**
- 一句话看懂: 它在做的事：Vision-Language-Action Models (VLAs) have shown remarkable progress towards embodied intelligence.
- 你可能会关心: Observing and Controlling Features in Vision-Language-Action Models（cs.RO）
- 中文题目（意译）: Observing and 控制 特征 in 视觉-语言-动作 模型
- 这篇在讲什么: 视觉-语言-动作 模型s (VLAs) have shown remarkable progress towards embodied intelligence.
- 它怎么做: In this work, 提出了 to close this gap by introducing and analyzing two main concepts: feature-observability and feature-controllability.
- 得出了什么结果: Our 结果显示 that targeted, lightweight interventions can reliably steer a robot's behavior while preserving closed-loop capabilities.
- 可能的影响: 视觉-语言-动作 模型s (VLAs) have shown remarkable progress towards embodied intelligence.
- arXiv: http://arxiv.org/abs/2603.05487v1
## 🔥 今日热度 Top 5（新鲜度+关键词+HN提及+代码线索）
1. **SurvHTE-Bench: A Benchmark for Heterogeneous Treatment Effect Estimation in Survival Analysis**
- arXiv: http://arxiv.org/abs/2603.05483v1
- 类别: cs.LG | HotScore: 32.79 | 作者: Shahriar Noroozizadeh, Xiaobin Shen, Jeremy C. Weiss
- 类别: cs.LG | HotScore: 32.67 | 作者: Shahriar Noroozizadeh, Xiaobin Shen, Jeremy C. Weiss
- 速读: SurvHTE-Bench: A Benchmark for Heterogeneous Treatment Effect Estimation in Survival An...（cs.LG）
2. **Accelerating Text-to-Video Generation with Calibrated Sparse Attention**
- arXiv: http://arxiv.org/abs/2603.05503v1
- 类别: cs.CV | HotScore: 27.9 | 作者: Shai Yehezkel, Shahar Yadin, Noam Elata
- 类别: cs.CV | HotScore: 27.77 | 作者: Shai Yehezkel, Shahar Yadin, Noam Elata
- 速读: Accelerating Text-to-Video Generation with Calibrated Sparse Attention（cs.CV）
3. **Observing and Controlling Features in Vision-Language-Action Models**
- arXiv: http://arxiv.org/abs/2603.05487v1
- 类别: cs.RO | HotScore: 27.81 | 作者: Hugo Buurmeijer, Carmen Amo Alonso, Aiden Swann
- 类别: cs.RO | HotScore: 27.69 | 作者: Hugo Buurmeijer, Carmen Amo Alonso, Aiden Swann
- 速读: Observing and Controlling Features in Vision-Language-Action Models（cs.RO）
4. **Towards Provably Unbiased LLM Judges via Bias-Bounded Evaluation**
- arXiv: http://arxiv.org/abs/2603.05485v1
- 类别: cs.AI | HotScore: 26.8 | 作者: Benjamin Feuer, Lucas Rosenblatt, Oussama Elachqar
- 类别: cs.AI | HotScore: 26.67 | 作者: Benjamin Feuer, Lucas Rosenblatt, Oussama Elachqar
- 速读: Towards Provably Unbiased LLM Judges via Bias-Bounded Evaluation（cs.AI）
5. **An interpretable prototype parts-based neural network for medical tabular data**
- arXiv: http://arxiv.org/abs/2603.05423v1
- 类别: cs.LG | HotScore: 25.83 | 作者: Jacek Karolczak, Jerzy Stefanowski
- 类别: cs.LG | HotScore: 25.71 | 作者: Jacek Karolczak, Jerzy Stefanowski
- 速读: An interpretable prototype parts-based neural network for medical tabular data（cs.LG）
## 🆕 最新上新 Top 10