21:48
Qwen2.5-VL Technical Report—No Blinks Allowed! (Paper Walkthrough)
11:09
Large Language Diffusion Models (Paper Walkthrough)
18:19
DeepSeek new paper—Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention
12:42
Beyond Next-Token Guessing: LLM Pretraining with Continuous Concepts (Paper Walkthrough)
14:08
Animate Anyone 2: High-Fidelity Character Image Animation with Environment Affordance
16:12
On the Geometry of Deep Learning (Inspired by MLST's latest: Neural Nets Are Elastic Origami)
13:27
Distill or Drill? Distillation Scaling Laws (Paper Walkthrough)
09:59
Harnessing Language's Fractal Geometry with Recursive Inference Scaling (Paper Walkthrough)
13:08
Deep Networks Always Grok & Here is Why (Inspired by MLST's latest: Neural Nets Are Elastic Origami)
15:12
Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling (Paper Walkthru)
30:32
Goku: Flow Based Video Generative Foundation Models (Paper Walkthrough)
21:37
Gold-medalist Performance in Solving Olympiad Geometry with AlphaGeometry2 (Paper Walkthrough)
06:57
Feb 7, 2025 🚗New AI Papers Drive-Thru: LLM, IMO geometry, TD learning, VectorQ, omni-modal, Robot
13:24
Vision-Language Model Dialog Games for Self-Improvement | From Google DeepMind (Paper Walkthrough)
04:44
Feb 6, 2025 🚗New AI Papers Drive-Thru: VLM, InverseRL, LLMfast, envAI, LiDAR NeRF, fedAdam, DataFree
16:01
Sparse VideoGen: Accelerating Video Diffusion Transformers with Spatial-Temporal Sparsity
46:54
Feb 5, 2025 🚗New AI Papers Drive-Thru: RL, Diffusion, Transformer, Contrastive Learning, Adversarial
11:07
VideoJAM: Joint Appearance-Motion Representations for Enhanced Motion Generation (Paper Walkthru)
42:41
Feb 4, 2025 🚗New AI Papers Drive-Thru: Alignment, diffusion, PINN, GNN, medical image, data synergy
14:59
OmniHuman-1: Now Your AI Avatar Can Dance, Sing, and Wave! (Paper Walkthrough)
25:48
Feb 3, 2025 🚗New AI Papers Drive-Thru: LLM, Diffusion, GNN, RL, Low-Rank, Edge, Meta-Learning & More
14:01
Wait, Think Again!—Simple test-time scaling (Paper Walkthrough)
12:10
SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-training (PaperWalkthru)
12:59
Critique Fine-Tuning: Learning to Critique is More Effective than Learning to Imitate
16:58
Towards General-Purpose Model-Free Reinforcement Learning | ICLR 2025 (Paper Walkthrough)
25:04
DeepSeek-Prover-V1.5: Theorem proofs? Cracked. Next!🎲
11:16
DeepSeek's Multimodal Launch—Janus-Pro Tech Report (Paper Walkthrough)
10:33
Chain-of-Retrieval Augmented Generation (Paper Walkthrough)
28:08
UI-TARS: Pioneering Automated GUI Interaction with Native Agents (Paper Walkthrough)
27:16
VideoLLaMA 3: Frontier Multimodal Foundation Models for Image and Video Understanding
18:42
Agent-R: Training Language Model Agents to Reflect via Iterative Self-Training (Paper Walkthrough)
14:01
Go-with-the-Flow: Motion-Controllable Video Diffusion Models Using Real-Time Warped Noise
13:08
Evolving Deeper LLM Thinking (Paper Walkthrough)
18:27
Kimi K1.5 Technical Report: Scaling Reinforcement Learning with LLMs (Paper Walkthrough)
19:22
DeepSeek-R1: Open Source Challenging OpenAI o1 (Paper Walkthrough)
26:18
Inference-Time Scaling for Diffusion Models beyond Scaling Denoising Steps (Paper Walkthrough)
18:56
MiniCPM-V: A GPT-4V Level MLLM on Your Phone (Paper Walkthrough)
10:37
MangaNinja: Line Art Colorization with Precise Reference Following (Paper Walkthrough)
29:11
MiniMax-01: Scaling Foundation Models with Lightning Attention (Paper Walkthrough)
00:39
Minimax's sweet PDF-on-the-side feature makes paper reading and live QA so much easier!🍭
11:51
OmniManip: Robotic Manipulation via Object-Centric Interaction Primitives as Spatial Constraints
18:32
Behind Kokoro TTS: StyleTTS 2 through Style Diffusion and Adversarial Training (Paper Walkthrough)
44:01
NVIDIA's Cosmos World Foundation Model Platform for Physical AI (Paper Walkthrough)
17:44
The GAN is dead; long live the GAN! A Modern GAN Baseline (Paper Walkthrough)
20:11
rStar-Math: Small LLMs Can Master Math Reasoning with Self-Evolved Deep Thinking (Paper Walkthrough)
15:07
Sa2VA: Marrying SAM2 with LLaVA for Dense Grounded Understanding of Images & Videos (Paper Walkthru)
15:09
ProTracker: Probabilistic Integration for Robust and Accurate Point Tracking (Paper Walkthrough)
09:04
OpenAI o1 Stumbles on Putnam: A True Test of Reasoning! (Paper Walkthrough)
17:13
ICLR: In-Context Learning of Representations (Paper Walkthrough)
22:59
4.5m (Suspected) Fake Stars in GitHub: A Growing Spiral of Popularity Contests, Scams, and Malware
15:16
ICONS: Influence Consensus for Vision-Language Data Selection (Paper Walkthrough)
22:32
4D Gaussian Splatting: Modeling Dynamic Scenes with Native 4D Primitives (Paper Walkthrough)
14:16
Trellis img-to-3d -- Structured 3D Latents for Scalable and Versatile 3D Generation (Paper Walkthru)
20:06
Do NOT Think That Much for 2+3=? On the Overthinking of o1-Like LLMs (Paper Walkthrough)
15:23
LLMs Hallucinate? Improving Factuality with Explicit Working Memory (Paper Walkthrough)
38:49
DeepSeek-V3 Technical Report Walkthrough
15:48
Navigation World Models | Latest from Yann LeCun's Team (Paper Walkthrough)
14:45
Adam on Local Time: Addressing Nonstationarity in RL with Relative Adam Timesteps (Paper Walkthru)
14:47
The Language of Motion: Unifying Verbal and Non-verbal Language of 3D Human Motion (Paper Walkthru)
14:58
Guiding a Diffusion Model with a Bad Version of Itself -- NeurIPS2024 Runner-Up (Paper Walkthrough)