Add pages for volume v260

Gemfile

@@ -0,0 +1,15 @@
+source "https://rubygems.org"
+
+git_source(:github) {|repo_name| "https://github.com/#{repo_name}" }
+
+gem 'jekyll'
+
+group :jekyll_plugins do
+  gem 'github-pages'
+  gem 'jekyll-remote-theme'
+  gem 'jekyll-include-cache'
+  gem 'webrick'
+end
+
+# gem "rails"
+

README.md

@@ -0,0 +1,22 @@
+# PMLR 260
+
+To suggest fixes to this volume please make a pull request containing the changes requested and a justification for the changes.
+
+To edit the details of this conference work edit the [_config.yml](./_config.yml) file and submit a pull request.
+
+To make changes to the individual paper details, edit the associated paper file in the [./_posts](./_posts) subdirectory.
+
+For details of how to publish in PMLR please check https://proceedings.mlr.press/faq.html
+
+For details of what is required to submit a proceedings please check https://proceedings.mlr.press/spec.html
+
+
+
+Published as Volume 260 by the Proceedings of Machine Learning Research on 14 January 2025.
+
+Volume Edited by:
+  * Vu Nguyen
+  * Hsuan-Tien Lin
+
+Series Editors:
+  * Neil D. Lawrence

_config.yml

@@ -0,0 +1,89 @@
+---
+booktitle: Proceedings of the 16th Asian Conference on Machine Learning
+shortname: ACML
+publisher: PMLR
+published: 2025-01-14
+start: &1 2024-12-05
+end: 2024-12-08
+series: Proceedings of Machine Learning Research
+volume: '260'
+year: '2025'
+layout: proceedings
+issn: 2640-3498
+id: ACML2024
+month: 0
+cycles: false
+bibtex_editor: Nguyen, Vu and Lin, Hsuan-Tien
+editor:
+- given: Vu
+  family: Nguyen
+- given: Hsuan-Tien
+  family: Lin
+title: Proceedings of Machine Learning Research
+description: |
+  Proceedings of the 16th Asian Conference on Machine Learning
+    Held in Hanoi, Vietnam on 05-08 December 2024
+
+  Published as Volume 260 by the Proceedings of Machine Learning Research on 14 January 2025.
+
+  Volume Edited by:
+    Vu Nguyen
+    Hsuan-Tien Lin
+
+  Series Editors:
+    Neil D. Lawrence
+date_str: 05--08 Dec
+url: https://proceedings.mlr.press
+author:
+  name: PMLR
+baseurl: "/v260"
+twitter_username: MLResearchPress
+github_username: mlresearch
+markdown: kramdown
+exclude:
+- README.md
+- Gemfile
+- ".gitignore"
+plugins:
+- jekyll-feed
+- jekyll-seo-tag
+- jekyll-remote-theme
+remote_theme: mlresearch/jekyll-theme
+style: pmlr
+permalink: "/:title.html"
+ghub:
+  edit: true
+  repository: v260
+display:
+  copy_button:
+    bibtex: true
+    endnote: true
+    apa: true
+  comments: false
+volume_type: Volume
+volume_dir: v260
+email: ''
+conference:
+  name: Asian Conference on Machine Learning
+  url: https://www.acml-conf.org/2024/
+  location: Hanoi, Vietnam
+  dates:
+  - *1
+  - 2024-12-06
+  - 2024-12-07
+  - 2024-12-08
+analytics:
+  google:
+    tracking_id: UA-92432422-1
+link_visibility:
+  openreview: true
+  pdf: true
+  supplementary: true
+  software: true
+  video: true
+  arxiv: true
+  doi: true
+  website: true
+orig_bibfile: "/Users/neil/mlresearch/v260/acml2024.bib"
+# Site settings
+# Original source:  /Users/neil/mlresearch/v260/acml2024.bib

_posts/2025-01-14-aravindan25a.md

@@ -0,0 +1,65 @@
+---
+title: 'EVaDE : Event-Based Variational Thompson Sampling for Model-Based Reinforcement
+  Learning'
+booktitle: Proceedings of the 16th Asian Conference on Machine Learning
+year: '2025'
+volume: '260'
+series: Proceedings of Machine Learning Research
+month: 0
+publisher: PMLR
+pdf: https://raw.githubusercontent.com/mlresearch/v260/main/assets/aravindan25a/aravindan25a.pdf
+url: https://proceedings.mlr.press/v260/aravindan25a.html
+software: https://tinyurl.com/3zb8nywx
+openreview: OYlNXMMSXB
+abstract: Posterior Sampling for Reinforcement Learning (PSRL) is a well-known algorithm
+  that augments model-based reinforcement learning (MBRL) algorithms with Thompson
+  sampling. PSRL maintains posterior distributions of the environment transition dynamics
+  and the reward function, which are intractable for tasks with high-dimensional state
+  and action spaces. Recent works show that dropout, used in conjunction with neural
+  networks, induces variational distributions that can approximate these posteriors.
+  In this paper, we propose Event-based Variational Distributions for Exploration
+  (EVaDE), which are variational distributions that are useful for MBRL, especially
+  when the underlying domain is object-based. We leverage the general domain knowledge
+  of object-based domains to design three types of event-based convolutional layers
+  to direct exploration. These layers rely on Gaussian dropouts and are inserted between
+  the layers of the deep neural network model to help facilitate variational Thompson
+  sampling. We empirically show the effectiveness of EVaDE-equipped Simulated Policy
+  Learning (EVaDE-SimPLe) on the 100K Atari game suite.
+layout: inproceedings
+issn: 2640-3498
+id: aravindan25a
+tex_title: "{EVaDE }: {E}vent-Based Variational Thompson Sampling for Model-Based
+  Reinforcement Learning"
+firstpage: 559
+lastpage: 574
+page: 559-574
+order: 559
+cycles: false
+bibtex_editor: Nguyen, Vu and Lin, Hsuan-Tien
+editor:
+- given: Vu
+  family: Nguyen
+- given: Hsuan-Tien
+  family: Lin
+bibtex_author: Aravindan, Siddharth and Mittal, Dixant and Lee, Wee Sun
+author:
+- given: Siddharth
+  family: Aravindan
+- given: Dixant
+  family: Mittal
+- given: Wee Sun
+  family: Lee
+date: 2025-01-14
+address:
+container-title: Proceedings of the 16th Asian Conference on Machine Learning
+genre: inproceedings
+issued:
+  date-parts:
+  - 2025
+  - 1
+  - 14
+extras:
+- label: Supplementary PDF
+  link: https://raw.githubusercontent.com/mlresearch/v260/main/assets/assets/aravindan25a/aravindan25a-supp.pdf
+# Format based on Martin Fenner's citeproc: https://blog.front-matter.io/posts/citeproc-yaml-for-bibliographies/
+---

_posts/2025-01-14-bougie25a.md

@@ -0,0 +1,64 @@
+---
+title: 'Exploring Beyond Curiosity Rewards: Language-Driven Exploration in RL'
+booktitle: Proceedings of the 16th Asian Conference on Machine Learning
+year: '2025'
+volume: '260'
+series: Proceedings of Machine Learning Research
+month: 0
+publisher: PMLR
+pdf: https://raw.githubusercontent.com/mlresearch/v260/main/assets/bougie25a/bougie25a.pdf
+url: https://proceedings.mlr.press/v260/bougie25a.html
+openreview: qHv7qTETsw
+abstract: 'Sparse rewards pose a significant challenge for many reinforcement learning
+  algorithms, which struggle in the absence of a dense, well-shaped reward function.
+  Drawing inspiration from the curiosity exhibited in animals, intrinsically-driven
+  methods overcome this drawback by incentivizing agents to explore novel states.
+  Yet, in the absence of domain-specific priors, sample efficiency is hindered as
+  most discovered novelty has little relevance to the true task reward. We present
+  iLLM, a curiosity-driven approach that leverages the inductive bias of foundation
+  models — Large Language Models, as a source of information about plausibly useful
+  behaviors. Two tasks are introduced for shaping exploration: 1) action generation
+  and 2) history compression, where the language model is prompted with a description
+  of the state-action trajectory. We further propose a technique for mapping state-action
+  pairs to pretrained token embeddings of the language model in order to alleviate
+  the need for explicit textual descriptions of the environment. By distilling prior
+  knowledge from large language models, iLLM encourages agents to discover diverse
+  and human-meaningful behaviors without requiring direct human intervention. We evaluate
+  the proposed method on BabyAI-Text, MiniHack, Atari games, and Crafter tasks, demonstrating
+  higher sample efficiency compared to prior curiosity-driven approaches.'
+layout: inproceedings
+issn: 2640-3498
+id: bougie25a
+tex_title: "{Exploring Beyond Curiosity Rewards}: {L}anguage-Driven Exploration in
+  {RL}"
+firstpage: 127
+lastpage: 142
+page: 127-142
+order: 127
+cycles: false
+bibtex_editor: Nguyen, Vu and Lin, Hsuan-Tien
+editor:
+- given: Vu
+  family: Nguyen
+- given: Hsuan-Tien
+  family: Lin
+bibtex_author: Bougie, Nicolas and Watanabe, Narimasa
+author:
+- given: Nicolas
+  family: Bougie
+- given: Narimasa
+  family: Watanabe
+date: 2025-01-14
+address:
+container-title: Proceedings of the 16th Asian Conference on Machine Learning
+genre: inproceedings
+issued:
+  date-parts:
+  - 2025
+  - 1
+  - 14
+extras:
+- label: Supplementary PDF
+  link: https://raw.githubusercontent.com/mlresearch/v260/main/assets/assets/bougie25a/bougie25a-supp.pdf
+# Format based on Martin Fenner's citeproc: https://blog.front-matter.io/posts/citeproc-yaml-for-bibliographies/
+---

_posts/2025-01-14-cai25a.md

@@ -0,0 +1,75 @@
+---
+title: 'FTP: A Human Pose Estimation Method Integrating Temporal and Fine-Grained
+  Feature Fusion'
+booktitle: Proceedings of the 16th Asian Conference on Machine Learning
+year: '2025'
+volume: '260'
+series: Proceedings of Machine Learning Research
+month: 0
+publisher: PMLR
+pdf: https://raw.githubusercontent.com/mlresearch/v260/main/assets/cai25a/cai25a.pdf
+url: https://proceedings.mlr.press/v260/cai25a.html
+openreview: 9XSm6cUhvS
+abstract: Human pose estimation is a significant research direction in the field of
+  computer vision, with critical applications in human motion reconstruction and analysis.
+  Currently proposed human pose estimation methods primarily focus on single-modality
+  sensor information, such as RGB images and LiDAR point clouds. While these methods
+  have achieved promising results within their respective domains, they remain limited
+  by the inherent deficiencies of each modality, hindering their applicability across
+  diverse real-world scenarios. With the recent introduction of numerous multi-modality
+  human pose datasets, multi-modality approaches have begun to develop. However, existing
+  multi-modality fusion methods mainly consider the global feature relationships between
+  different modalities, without modeling finer-grained features or the dynamic temporal
+  relationships between modalities. To address this issue, we propose a novel pipeline
+  that integrates point cloud and image features, explicitly encoding fine-grained
+  features and dynamic temporal relationships between the two modalities. Additionally,
+  we employ a discriminator structure for semi-supervised training. Extensive experiments
+  demonstrate that our method achieves state-of-the-art (SOTA) performance compared
+  to previous methods.
+layout: inproceedings
+issn: 2640-3498
+id: cai25a
+tex_title: "{FTP}: {A} Human Pose Estimation Method Integrating Temporal and Fine-Grained
+  Feature Fusion"
+firstpage: 858
+lastpage: 872
+page: 858-872
+order: 858
+cycles: false
+bibtex_editor: Nguyen, Vu and Lin, Hsuan-Tien
+editor:
+- given: Vu
+  family: Nguyen
+- given: Hsuan-Tien
+  family: Lin
+bibtex_author: Cai, Shuqiang and Ma, Chennan and Wang, Xin and Lin, Li and Yan, Ming
+  and Lin, Xincheng and Fan, Shuqi and Shen, Siqi
+author:
+- given: Shuqiang
+  family: Cai
+- given: Chennan
+  family: Ma
+- given: Xin
+  family: Wang
+- given: Li
+  family: Lin
+- given: Ming
+  family: Yan
+- given: Xincheng
+  family: Lin
+- given: Shuqi
+  family: Fan
+- given: Siqi
+  family: Shen
+date: 2025-01-14
+address:
+container-title: Proceedings of the 16th Asian Conference on Machine Learning
+genre: inproceedings
+issued:
+  date-parts:
+  - 2025
+  - 1
+  - 14
+extras: []
+# Format based on Martin Fenner's citeproc: https://blog.front-matter.io/posts/citeproc-yaml-for-bibliographies/
+---