Daily Giants on arXiv

•
In today’s fast-paced world of research, the volume of papers uploaded to arXiv everyday is overwhelming.
•
Everyday, we curate and archive the most significant research papers published by leading groups.
•
Sit on the shoulders of tech giants and gain a clearer perspective of the ever-evolving landscape of innovation.
Search
Tags
Title
URL
Uploaded at
Meta
Multi-SpatialMLLM: Multi-Frame Spatial Understanding with Multi-Modal Large Language Models
Open
https://arxiv.org/abs/2505.17015
2025/05/23 14:04
Google
DeepMind
Understanding Prompt Tuning and In-Context Learning via Meta-Learning
Open
https://arxiv.org/abs/2505.17010
2025/05/23 14:04
Salesforce
LaViDa: A Large Diffusion Language Model for Multimodal Understanding
Open
https://arxiv.org/abs/2505.16839
2025/05/23 14:04
Microsoft
Breaking mBad! Supervised Fine-tuning for Cross-Lingual Detoxification
Open
https://arxiv.org/abs/2505.16722
2025/05/23 14:04
Meta
Beyond Induction Heads: In-Context Meta Learning Induces Multi-Phase Circuit Emergence
Open
https://arxiv.org/abs/2505.16694
2025/05/23 14:04
Microsoft
One-Step Diffusion-Based Image Compression with Semantic Distillation
Open
https://arxiv.org/abs/2505.16687
2025/05/23 14:04
Apple
Accuracy vs. Accuracy: Computational Tradeoffs Between Classification Rates and Utility
Open
https://arxiv.org/abs/2505.16494
2025/05/23 14:04
Meta
ReflectEvo: Improving Meta Introspection of Small LLMs by Learning Self-Reflection
Open
https://arxiv.org/abs/2505.16475
2025/05/23 14:04
Microsoft
PaTH Attention: Position Encoding via Accumulating Householder Transformations
Open
https://arxiv.org/abs/2505.16381
2025/05/23 14:04
Microsoft
TRAIL: Transferable Robust Adversarial Images via Latent diffusion
Open
https://arxiv.org/abs/2505.16166
2025/05/23 14:04
Google
DeepMind
Dimension-adapted Momentum Outscales SGD
Open
https://arxiv.org/abs/2505.16098
2025/05/23 14:04
Microsoft
Can AI Read Between The Lines? Benchmarking LLMs On Financial Nuance
Open
https://arxiv.org/abs/2505.16090
2025/05/23 14:04
Facebook
Meta
Aug2Search: Enhancing Facebook Marketplace Search with LLM-Generated Synthetic Data Augmentation
Open
https://arxiv.org/abs/2505.16065
2025/05/23 14:04
Google
CP-LLM: Context and Pixel Aware Large Language Model for Video Quality Assessment
Open
https://arxiv.org/abs/2505.16025
2025/05/23 14:04
Google
What Lives? A meta-analysis of diverse opinions on the definition of life
Open
https://arxiv.org/abs/2505.15849
2025/05/23 14:04
Microsoft
Dion: Distributed Orthonormalized Updates
Open
https://arxiv.org/abs/2504.05295
2025/05/23 14:04
Microsoft
Through the LLM Looking Glass: A Socratic Probing of Donkeys, Elephants, and Markets
Open
https://arxiv.org/abs/2503.16674
2025/05/23 14:04
OpenAI
Split Gibbs Discrete Diffusion Posterior Sampling
Open
https://arxiv.org/abs/2503.01161
2025/05/23 14:04
Google
LCIRC: A Recurrent Compression Approach for Efficient Long-form Context and Query Dependent Modeling in LLMs
Open
https://arxiv.org/abs/2502.06139
2025/05/23 14:04
Apple
Is a Peeled Apple Still Red? Evaluating LLMs' Ability for Conceptual Combination with Property Type
Open
https://arxiv.org/abs/2502.06086
2025/05/23 14:04
Microsoft
SimSort: A Data-Driven Framework for Spike Sorting by Large-Scale Electrophysiology Simulation
Open
https://arxiv.org/abs/2502.03198
2025/05/23 14:04
Meta
Diverse Preference Optimization
Open
https://arxiv.org/abs/2501.18101
2025/05/23 14:04
Microsoft
MoE-CAP: Benchmarking Cost, Accuracy and Performance of Sparse Mixture-of-Experts Systems
Open
https://arxiv.org/abs/2412.07067
2025/05/23 14:04
Microsoft
Permissive Information-Flow Analysis for Large Language Models
Open
https://arxiv.org/abs/2410.03055
2025/05/23 14:04
Google
Logit Scaling for Out-of-Distribution Detection
Open
https://arxiv.org/abs/2409.01175
2025/05/23 14:04
Load more
COUNT26

Contact Us

•
We value your feedback and inquiries.
•
Please feel free to reach out to us using the information below.