ChatPaper - Search

Users
Tweets

ChatPaper.ai @ChatPaper_ai

May 6

🔥 Daily AI Paper (2026-05-05) 📄 MolmoAct2: Action Reasoning Models for Real-world Deployment 🔗 chatpaper.ai/dashboard/paper… #AI #ML #ChatPaper

MolmoAct2: Action Reasoning Models for Real-world Deployment

Vision-Language-Action (VLA) models aim to provide a single generalist controller for robots, but today's systems fall short on the criteria that matter for real-world deployment. Frontier models are...

2

6

354

ChatPaper.ai @ChatPaper_ai

Mar 30

🔥 Daily AI Paper (2026-03-27) 📄 PixelSmile: Toward Fine-Grained Facial Expression Editing 🔗 chatpaper.ai/dashboard/paper… #AI #ML #ChatPaper

PixelSmile: Toward Fine-Grained Facial Expression Editing

Fine-grained facial expression editing has long been limited by intrinsic semantic overlap. To address this, we construct the Flex Facial Expression (FFE) dataset with continuous affective annotati...

1

2

19

ChatPaper.ai @ChatPaper_ai

Mar 13

🔥 Daily AI Paper (2026-03-12) 📄 OpenClaw-RL: Train Any Agent Simply by Talking 🔗 chatpaper.ai/dashboard/paper… #AI #ML #ChatPaper

OpenClaw-RL: Train Any Agent Simply by Talking

Every agent interaction generates a next-state signal, namely the user reply, tool output, terminal or GUI state change that follows each action, yet no existing agentic RL system recovers it as a...

1

2

21

ChatPaper.ai @ChatPaper_ai

Feb 23

🔥 Daily AI Paper (2026-02-20) 📄 SpargeAttention2: Trainable Sparse Attention via Hybrid Top-k Top-p Masking and Distillation Fine-Tuning 🔗 chatpaper.ai/dashboard/paper… #AI #ML #ChatPaper

SpargeAttention2: Trainable Sparse Attention via Hybrid Top-k Top-p Masking and Distillation...

Many training-free sparse attention methods are effective for accelerating diffusion models. Recently, several works suggest that making sparse attention trainable can further increase sparsity while...

2

19

ChatPaper.ai @ChatPaper_ai

Feb 12

🔥 Daily AI Paper (2026-02-11) 📄 OPUS: Towards Efficient and Principled Data Selection in Large Language Model Pre-training in Every Iteration 🔗 chatpaper.ai/dashboard/paper… #AI #ML #ChatPaper

OPUS: Towards Efficient and Principled Data Selection in Large Language Model Pre-training in Every...

As high-quality public text approaches exhaustion, a phenomenon known as the Data Wall, pre-training is shifting from more tokens to better tokens. However, existing methods either rely on heuristic...

2

23

ChatPaper.ai @ChatPaper_ai

19 Dec 2025

🔥 Daily AI Paper (2025-12-18) 📄 Step-GUI Technical Report 🔗 chatpaper.ai/dashboard/paper… #AI #ML #ChatPaper

Step-GUI Technical Report

Recent advances in multimodal large language models unlock unprecedented opportunities for GUI automation. However, a fundamental challenge remains: how to efficiently acquire high-quality training...

2

66

ChatPaper.ai @ChatPaper_ai

14 Oct 2025

🔥 Daily AI Paper (2025-10-13) 📄 D2E: Scaling Vision-Action Pretraining on Desktop Data for Transfer to Embodied AI 🔗 chatpaper.ai/dashboard/paper… #AI #ML #ChatPaper

D2E: Scaling Vision-Action Pretraining on Desktop Data for Transfer to Embodied AI

Large language models leverage internet-scale text data, yet embodied AI remains constrained by the prohibitive costs of physical trajectory collection. Desktop environments -- particularly gaming --...

2

3

38

ChatPaper.ai @ChatPaper_ai

24 Sep 2025

🔥 Daily AI Paper (2025-09-23) 📄 LIMI: Less is More for Agency 🔗 chatpaper.ai/dashboard/paper… #AI #ML #ChatPaper

LIMI: Less is More for Agency

We define Agency as the emergent capacity of AI systems to function as autonomous agents actively discovering problems, formulating hypotheses, and executing solutions through self-directed engagem...

2

34

ChatPaper.ai @ChatPaper_ai

21 Sep 2025

🔥 Daily AI Paper (2025-09-19) 📄 ScaleCUA: Scaling Open-Source Computer Use Agents with Cross-Platform Data 🔗 chatpaper.ai/dashboard/paper… #AI #ML #ChatPaper

ScaleCUA: Scaling Open-Source Computer Use Agents with Cross-Platform Data

Vision-Language Models (VLMs) have enabled computer use agents (CUAs) that operate GUIs autonomously, showing great potential, yet progress is limited by the lack of large-scale, open-source computer...

2

24

ChatPaper.ai @ChatPaper_ai

20 Sep 2025

🔥 Daily AI Paper (2025-09-19) 📄 ScaleCUA: Scaling Open-Source Computer Use Agents with Cross-Platform Data 🔗 chatpaper.ai/dashboard/paper… #AI #ML #ChatPaper

ScaleCUA: Scaling Open-Source Computer Use Agents with Cross-Platform Data

Vision-Language Models (VLMs) have enabled computer use agents (CUAs) that operate GUIs autonomously, showing great potential, yet progress is limited by the lack of large-scale, open-source computer...

1

1

84

ChatPaper.ai @ChatPaper_ai

10 Sep 2025

🔥 Daily AI Paper (2025-09-09) 📄 Reverse-Engineered Reasoning for Open-Ended Generation 🔗 chatpaper.ai/dashboard/paper… #AI #ML #ChatPaper

Reverse-Engineered Reasoning for Open-Ended Generation

While the ``deep reasoning'' paradigm has spurred significant advances in verifiable domains like mathematics, its application to open-ended, creative generation remains a critical challenge. The two...

2

25

ChatPaper.ai @ChatPaper_ai

9 Sep 2025

🔥 Daily AI Paper (2025-09-08) 📄 Why Language Models Hallucinate 🔗 chatpaper.ai/dashboard/paper… #AI #ML #ChatPaper

Why Language Models Hallucinate

Like students facing hard exam questions, large language models sometimes guess when uncertain, producing plausible yet incorrect statements instead of admitting uncertainty. Such "hallucinations"...

2

18

ChatPaper.ai @ChatPaper_ai

3 Sep 2025

🔥 Daily AI Paper (2025-09-02) 📄 PVPO: Pre-Estimated Value-Based Policy Optimization for Agentic Reasoning 🔗 chatpaper.ai/dashboard/paper… #AI #ML #ChatPaper

PVPO: Pre-Estimated Value-Based Policy Optimization for Agentic Reasoning

Critic-free reinforcement learning methods, particularly group policies, have attracted considerable attention for their efficiency in complex tasks. However, these methods rely heavily on multiple...

2

18

ChatPaper.ai @ChatPaper_ai

1 Sep 2025

🔥 Daily AI Paper (2025-08-29) 📄 Pref-GRPO: Pairwise Preference Reward-based GRPO for Stable Text-to-Image Reinforcement Learning 🔗 chatpaper.ai/dashboard/paper… #AI #ML #ChatPaper

Pref-GRPO: Pairwise Preference Reward-based GRPO for Stable Text-to-Image Reinforcement Learning

Recent advancements highlight the importance of GRPO-based reinforcement learning methods and benchmarking in enhancing text-to-image (T2I) generation. However, current methods using pointwise reward...

1

2

17

ChatPaper.ai @ChatPaper_ai

31 Aug 2025

🔥 Daily AI Paper (2025-08-29) 📄 Pref-GRPO: Pairwise Preference Reward-based GRPO for Stable Text-to-Image Reinforcement Learning 🔗 chatpaper.ai/dashboard/paper… #AI #ML #ChatPaper

Pref-GRPO: Pairwise Preference Reward-based GRPO for Stable Text-to-Image Reinforcement Learning

Recent advancements highlight the importance of GRPO-based reinforcement learning methods and benchmarking in enhancing text-to-image (T2I) generation. However, current methods using pointwise reward...

1

3

26

ChatPaper.ai @ChatPaper_ai

29 Aug 2025

🔥 Daily AI Paper (2025-08-28) 📄 Beyond Transcription: Mechanistic Interpretability in ASR 🔗 chatpaper.ai/dashboard/paper… #AI #ML #ChatPaper

Beyond Transcription: Mechanistic Interpretability in ASR

Interpretability methods have recently gained significant attention, particularly in the context of large language models, enabling insights into linguistic representations, error detection, and...

2

22

ChatPaper.ai @ChatPaper_ai

27 Aug 2025

🔥 Daily AI Paper (2025-08-26) 📄 InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency 🔗 chatpaper.ai/dashboard/paper… #AI #ML #ChatPaper

InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency

We introduce InternVL 3.5, a new family of open-source multimodal models that significantly advances versatility, reasoning capability, and inference efficiency along the InternVL series. A key...

2

33

ChatPaper.ai @ChatPaper_ai

17 Aug 2025

🔥 Daily AI Paper (2025-08-15) 📄 We-Math 2.0: A Versatile MathBook System for Incentivizing Visual Mathematical Reasoning 🔗 chatpaper.ai/dashboard/paper… #AI #ML #ChatPaper

We-Math 2.0: A Versatile MathBook System for Incentivizing Visual Mathematical Reasoning

Multimodal Large Language Models (MLLMs) have demonstrated impressive capabilities across various tasks, but still struggle with complex mathematical reasoning. Existing research primarily focuses on...

3

18

ChatPaper.ai @ChatPaper_ai

14 Aug 2025

🔥 Daily AI Paper (2025-08-13) 📄 WebWatcher: Breaking New Frontier of Vision-Language Deep Research Agent 🔗 chatpaper.ai/dashboard/paper… #AI #ML #ChatPaper

WebWatcher: Breaking New Frontier of Vision-Language Deep Research Agent

Web agents such as Deep Research have demonstrated superhuman cognitive abilities, capable of solving highly challenging information-seeking problems. However, most research remains primarily...

17

ChatPaper.ai @ChatPaper_ai

13 Aug 2025

🔥 Daily AI Paper (2025-08-12) 📄 ReasonRank: Empowering Passage Ranking with Strong Reasoning Ability 🔗 chatpaper.ai/dashboard/paper… #AI #ML #ChatPaper

ReasonRank: Empowering Passage Ranking with Strong Reasoning Ability

Large Language Model (LLM) based listwise ranking has shown superior performance in many passage ranking tasks. With the development of Large Reasoning Models, many studies have demonstrated that...

2

11