ZeroGPU Explorers

community

AI & ML interests

None defined yet.

akhaliq

submitted 2 papers to Daily Papers 3 days ago

Visual Personalization Turing Test

Paper • 2601.22680 • Published 6 days ago • 2

Causal World Modeling for Robot Control

Paper • 2601.21998 • Published 7 days ago • 27

julien-c

submitted a paper to Daily Papers 6 days ago

Shaping capabilities with token-level data filtering

Paper • 2601.21571 • Published 7 days ago • 23

mlabonne

authored 2 papers 13 days ago

LFM2 Technical Report

Paper • 2511.23404 • Published Nov 28, 2025 • 52

Zero-Overhead Introspection for Adaptive Test-Time Compute

Paper • 2512.01457 • Published Dec 1, 2025 • 2

LXT

submitted a paper to Daily Papers 14 days ago

SAMTok: Representing Any Mask with Two Words

Paper • 2601.16093 • Published 14 days ago • 41

akhaliq

submitted a paper to Daily Papers 14 days ago

Motion 3-to-4: 3D Motion Reconstruction for 4D Synthesis

Paper • 2601.14253 • Published 16 days ago • 10

akhaliq

submitted a paper to Daily Papers 20 days ago

V-DPM: 4D Video Reconstruction with Dynamic Point Maps

Paper • 2601.09499 • Published 22 days ago • 9

akhaliq

submitted a paper to Daily Papers 22 days ago

UM-Text: A Unified Multimodal Model for Image Understanding

Paper • 2601.08321 • Published 23 days ago • 9

gagan3012

authored 2 papers 23 days ago

From RAG to Agentic RAG for Faithful Islamic Question Answering

Paper • 2601.07528 • Published 24 days ago

Prototypicality Bias Reveals Blindspots in Multimodal Evaluation Metrics

Paper • 2601.04946 • Published 28 days ago

akhaliq

submitted a paper to Daily Papers 28 days ago

ResTok: Learning Hierarchical Residuals in 1D Visual Tokenizers for Autoregressive Image Generation

Paper • 2601.03955 • Published 29 days ago • 3

mlabonne

posted an update about 1 month ago

Post

5486

New family of 1B models just dropped!

> LiquidAI/LFM2.5-1.2B-Base: 10T → 28T tokens
> LiquidAI/LFM2.5-1.2B-Instruct: new large-scale multi-stage RL
> LiquidAI/LFM2.5-1.2B-JP: our most polite model
> LiquidAI/LFM2.5-VL-1.6B: multi-image multilingual
> LiquidAI/LFM2.5-Audio-1.5B: 8x times faster, no quality loss

Super proud of this release 🤗

3 replies

·

akhaliq

submitted 2 papers to Daily Papers about 1 month ago

FlowBlending: Stage-Aware Multi-Model Sampling for Fast and High-Fidelity Video Generation

Paper • 2512.24724 • Published Dec 31, 2025 • 7

Dream2Flow: Bridging Video Generation and Open-World Manipulation with 3D Object Flow

Paper • 2512.24766 • Published Dec 31, 2025 • 9

akhaliq

submitted a paper to Daily Papers about 2 months ago

What matters for Representation Alignment: Global Information or Spatial Structure?

Paper • 2512.10794 • Published Dec 11, 2025 • 9

LXT

authored 4 papers about 2 months ago

DenseWorld-1M: Towards Detailed Dense Grounded Caption in the Real World

Paper • 2506.24102 • Published Jun 30, 2025

One Flight Over the Gap: A Survey from Perspective to Panoramic Vision

Paper • 2509.04444 • Published Sep 4, 2025

VimoRAG: Video-based Retrieval-augmented 3D Motion Generation for Motion Language Models

Paper • 2508.12081 • Published Aug 16, 2025

DiT360: High-Fidelity Panoramic Image Generation via Hybrid Training

Paper • 2510.11712 • Published Oct 13, 2025 • 31