@ChatPaper_ai profile picture
ChatPaper.ai @ChatPaper_ai

Make Knowledge Management Smarter, Learning and Work More Efficient

Joined August 2024
  • Tweets 272
  • Following 4
  • Followers 18
3 Photos and videos
๐Ÿ”ฅ Daily AI Paper (2026-05-14) ๐Ÿ“„ MinT: Managed Infrastructure for Training and Serving Millions of LLMs ๐Ÿ”— chatpaper.ai/dashboard/paperโ€ฆ #AI #ML #ChatPaper

MinT: Managed Infrastructure for Training and Serving Millions of LLMs

We present MindLab Toolkit (MinT), a managed infrastructure system for Low-Rank Adaptation (LoRA) post-training and online serving. MinT targets a setting where many trained policies are produced...

chatpaper.ai
15
๐Ÿ”ฅ Daily AI Paper (2026-05-13) ๐Ÿ“„ MemPrivacy: Privacy-Preserving Personalized Memory Management for Edge-Cloud Agents ๐Ÿ”— chatpaper.ai/dashboard/paperโ€ฆ #AI #ML #ChatPaper
8
๐Ÿ”ฅ Daily AI Paper (2026-05-12) ๐Ÿ“„ Qwen-Image-2.0 Technical Report ๐Ÿ”— chatpaper.ai/dashboard/paperโ€ฆ #AI #ML #ChatPaper

Qwen-Image-2.0 Technical Report

We present Qwen-Image-2.0, an omni-capable image generation foundation model that unifies high-fidelity generation and precise image editing within a single framework. Despite recent progress,...

chatpaper.ai
35
๐Ÿ”ฅ Daily AI Paper (2026-05-11) ๐Ÿ“„ Mean Mode Screaming: Mean--Variance Split Residuals for 1000-Layer Diffusion Transformers ๐Ÿ”— chatpaper.ai/dashboard/paperโ€ฆ #AI #ML #ChatPaper

Mean Mode Screaming: Mean--Variance Split Residuals for 1000-Layer Diffusion Transformers

Scaling Diffusion Transformers (DiTs) to hundreds of layers introduces a structural vulnerability: networks can enter a silent, mean-dominated collapse state that homogenizes token representations...

chatpaper.ai
10
๐Ÿ”ฅ Daily AI Paper (2026-05-08) ๐Ÿ“„ Skill1: Unified Evolution of Skill-Augmented Agents via Reinforcement Learning ๐Ÿ”— chatpaper.ai/dashboard/paperโ€ฆ #AI #ML #ChatPaper

Skill1: Unified Evolution of Skill-Augmented Agents via Reinforcement Learning

A persistent skill library allows language model agents to reuse successful strategies across tasks. Maintaining such a library requires three coupled capabilities. The agent selects a relevant...

chatpaper.ai
14
๐Ÿ”ฅ Daily AI Paper (2026-05-08) ๐Ÿ“„ Skill1: Unified Evolution of Skill-Augmented Agents via Reinforcement Learning ๐Ÿ”— chatpaper.ai/dashboard/paperโ€ฆ #AI #ML #ChatPaper

Skill1: Unified Evolution of Skill-Augmented Agents via Reinforcement Learning

A persistent skill library allows language model agents to reuse successful strategies across tasks. Maintaining such a library requires three coupled capabilities. The agent selects a relevant...

chatpaper.ai
25
๐Ÿ”ฅ Daily AI Paper (2026-05-08) ๐Ÿ“„ Skill1: Unified Evolution of Skill-Augmented Agents via Reinforcement Learning ๐Ÿ”— chatpaper.ai/dashboard/paperโ€ฆ #AI #ML #ChatPaper

Skill1: Unified Evolution of Skill-Augmented Agents via Reinforcement Learning

A persistent skill library allows language model agents to reuse successful strategies across tasks. Maintaining such a library requires three coupled capabilities. The agent selects a relevant...

chatpaper.ai
1
37
๐Ÿ”ฅ Daily AI Paper (2026-05-07) ๐Ÿ“„ Stream-R1: Reliability-Perplexity Aware Reward Distillation for Streaming Video Generation ๐Ÿ”— chatpaper.ai/dashboard/paperโ€ฆ #AI #ML #ChatPaper

Stream-R1: Reliability-Perplexity Aware Reward Distillation for Streaming Video Generation

Distillation-based acceleration has become foundational for making autoregressive streaming video diffusion models practical, with distribution matching distillation (DMD) as the de facto choice....

chatpaper.ai
9
๐Ÿ”ฅ Daily AI Paper (2026-05-06) ๐Ÿ“„ ARIS: Autonomous Research via Adversarial Multi-Agent Collaboration ๐Ÿ”— chatpaper.ai/dashboard/paperโ€ฆ #AI #ML #ChatPaper

ARIS: Autonomous Research via Adversarial Multi-Agent Collaboration

This report describes ARIS (Auto-Research-in-sleep), an open-source research harness for autonomous research, including its architecture, assurance mechanisms, and early deployment experience. The...

chatpaper.ai
16
๐Ÿ”ฅ Daily AI Paper (2026-05-05) ๐Ÿ“„ MolmoAct2: Action Reasoning Models for Real-world Deployment ๐Ÿ”— chatpaper.ai/dashboard/paperโ€ฆ #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...

chatpaper.ai
2
6
354
๐Ÿ”ฅ Daily AI Paper (2026-05-04) ๐Ÿ“„ UniVidX: A Unified Multimodal Framework for Versatile Video Generation via Diffusion Priors ๐Ÿ”— chatpaper.ai/dashboard/paperโ€ฆ #AI #ML #ChatPaper

UniVidX: A Unified Multimodal Framework for Versatile Video Generation via Diffusion Priors

Recent progress has shown that video diffusion models (VDMs) can be repurposed for diverse multimodal graphics tasks. However, existing methods often train separate models for each problem setting,...

chatpaper.ai
15
๐Ÿ”ฅ Daily AI Paper (2026-05-01) ๐Ÿ“„ Heterogeneous Scientific Foundation Model Collaboration ๐Ÿ”— chatpaper.ai/dashboard/paperโ€ฆ #AI #ML #ChatPaper

Heterogeneous Scientific Foundation Model Collaboration

Agentic large language model systems have demonstrated strong capabilities. However, their reliance on language as the universal interface fundamentally limits their applicability to many real-world...

chatpaper.ai
6
๐Ÿ”ฅ Daily AI Paper (2026-05-01) ๐Ÿ“„ Heterogeneous Scientific Foundation Model Collaboration ๐Ÿ”— chatpaper.ai/dashboard/paperโ€ฆ #AI #ML #ChatPaper

Heterogeneous Scientific Foundation Model Collaboration

Agentic large language model systems have demonstrated strong capabilities. However, their reliance on language as the universal interface fundamentally limits their applicability to many real-world...

chatpaper.ai
1
9
๐Ÿ”ฅ Daily AI Paper (2026-05-01) ๐Ÿ“„ Heterogeneous Scientific Foundation Model Collaboration ๐Ÿ”— chatpaper.ai/dashboard/paperโ€ฆ #AI #ML #ChatPaper

Heterogeneous Scientific Foundation Model Collaboration

Agentic large language model systems have demonstrated strong capabilities. However, their reliance on language as the universal interface fundamentally limits their applicability to many real-world...

chatpaper.ai
9
๐Ÿ”ฅ Daily AI Paper (2026-04-30) ๐Ÿ“„ GLM-5V-Turbo: Toward a Native Foundation Model for Multimodal Agents ๐Ÿ”— chatpaper.ai/dashboard/paperโ€ฆ #AI #ML #ChatPaper

GLM-5V-Turbo: Toward a Native Foundation Model for Multimodal Agents

We present GLM-5V-Turbo, a step toward native foundation models for multimodal agents. As foundation models are increasingly deployed in real environments, agentic capability depends not only on...

chatpaper.ai
1
18
๐Ÿ”ฅ Daily AI Paper (2026-04-29) ๐Ÿ“„ Recursive Multi-Agent Systems ๐Ÿ”— chatpaper.ai/dashboard/paperโ€ฆ #AI #ML #ChatPaper

Recursive Multi-Agent Systems

Recursive or looped language models have recently emerged as a new scaling axis by iteratively refining the same model computation over latent states to deepen reasoning. We extend such scaling...

chatpaper.ai
1
1
50
๐Ÿ”ฅ Daily AI Paper (2026-04-28) ๐Ÿ“„ From Skills to Talent: Organising Heterogeneous Agents as a Real-World Company ๐Ÿ”— chatpaper.ai/dashboard/paperโ€ฆ #AI #ML #ChatPaper

From Skills to Talent: Organising Heterogeneous Agents as a Real-World Company

Individual agent capabilities have advanced rapidly through modular skills and tool integrations, yet multi-agent systems remain constrained by fixed team structures, tightly coupled coordination...

chatpaper.ai
1
12
๐Ÿ”ฅ Daily AI Paper (2026-04-27) ๐Ÿ“„ Agentic World Modeling: Foundations, Capabilities, Laws, and Beyond ๐Ÿ”— chatpaper.ai/dashboard/paperโ€ฆ #AI #ML #ChatPaper

Agentic World Modeling: Foundations, Capabilities, Laws, and Beyond

As AI systems move from generating text to accomplishing goals through sustained interaction, the ability to model environment dynamics becomes a central bottleneck. Agents that manipulate objects,...

chatpaper.ai
68
๐Ÿ”ฅ Daily AI Paper (2026-04-24) ๐Ÿ“„ LLaTiSA: Towards Difficulty-Stratified Time Series Reasoning from Visual Perception to Semantics ๐Ÿ”— chatpaper.ai/dashboard/paperโ€ฆ #AI #ML #ChatPaper

LLaTiSA: Towards Difficulty-Stratified Time Series Reasoning from Visual Perception to Semantics

Comprehensive understanding of time series remains a significant challenge for Large Language Models (LLMs). Current research is hindered by fragmented task definitions and benchmarks with inherent...

chatpaper.ai
14
๐Ÿ”ฅ Daily AI Paper (2026-04-24) ๐Ÿ“„ LLaTiSA: Towards Difficulty-Stratified Time Series Reasoning from Visual Perception to Semantics ๐Ÿ”— chatpaper.ai/dashboard/paperโ€ฆ #AI #ML #ChatPaper

LLaTiSA: Towards Difficulty-Stratified Time Series Reasoning from Visual Perception to Semantics

Comprehensive understanding of time series remains a significant challenge for Large Language Models (LLMs). Current research is hindered by fragmented task definitions and benchmarks with inherent...

chatpaper.ai
9
Load more