Solaris: Building a Multiplayer Video World Model in Minecraft

by Georgy Savva et al.

Soft Contamination Means Benchmarks Test Shallow Generalization

by Ari Spiesberger et al.

Visually Prompted Benchmarks Are Surprisingly Fragile

by Haiwen Feng et al.

BabyVision: Visual Reasoning Beyond Language

by Liang Chen et al.

Vision Encoders in Vision-Language Models: A Survey

by Han Xiao

Next-Embedding Prediction Makes Strong Vision Learners

by Sihan Xu et al.

What Kind of Reasoning (if any) is an LLM actually doing? On the Stochastic Nature and Abductive Appearance of Large Language Models

by Luciano Floridi et al.

Olmo 3

by Team Olmo

On the Interplay of Pre-Training, Mid-Training, and RL on Reasoning Language Models

by Charlie Zhang et al.

Lumine: An Open Recipe for Building Generalist Agents in 3D Open Worlds

by Weihao Tan et al.

Questioning the Stability of Visual Question Answering

by Amir Rosenfeld et al.

OpenVision 2: A Family of Generative Pretrained Visual Encoders for Multimodal Learning

by Yanqing Liu et al.

Subliminal Learning: Language models transmit behavioral traits via hidden signals in data

by Alex Cloud et al.

The Term 'Agent' Has Been Diluted Beyond Utility and Requires Redefinition

by Brinnae Bent

Vision Language Models are Biased

by An Vo et al.

GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models

by GLM-4. 5 Team et al.

Bifrost-1: Bridging Multimodal LLMs and Diffusion Models with Patch-level CLIP Latents

by Han Lin et al.

Seed1.5-VL Technical Report

by Dong Guo et al.

Emerging Properties in Unified Multimodal Pretraining

by Chaorui Deng et al.

Harnessing the Universal Geometry of Embeddings

by Rishi Jha et al.

Transfer between Modalities with MetaQueries

by Xichen Pan et al.

Bring Reason to Vision: Understanding Perception and Reasoning through Model Merging

by Shiqi Chen et al.

Rethinking Visual Layer Selection in Multimodal LLMs

by Haoran Chen et al.

Perception Encoder: The best visual embeddings are not at the output of the network

by Daniel Bolya et al.

Scaling Laws for Native Multimodal Models

by Mustafa Shukor et al.

Science-T2I: Addressing Scientific Illusions in Image Synthesis

by Jialuo Li et al.

Token-Shuffle: Towards High-Resolution Image Generation with Autoregressive Models

by Xu Ma et al.

Scaling Language-Free Visual Representation Learning

by David Fan et al.

A Decade's Battle on Dataset Bias: Are We There Yet?

by Zhuang Liu et al.

Sparse Autoencoders for Scientifically Rigorous Interpretation of Vision Models

by Samuel Stevens et al.

Pretrained Transformers as Universal Computation Engines

by Kevin Lu et al.

Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach

by Jonas Geiping et al.

Are Vision Language Models Texture or Shape Biased and Can We Steer Them?

by Paul Gavrikov et al.

Open Problems in Mechanistic Interpretability

by Lee Sharkey et al.

Why Do We Need Weight Decay in Modern Deep Learning?

by Francesco D'Angelo et al.

Vision-Language Models Do Not Understand Negation

by Kumail Alhamoud et al.

ICONS: Influence Consensus for Vision-Language Data Selection

by Xindi Wu et al.

The GAN is dead; long live the GAN! A Modern GAN Baseline

by Yiwen Huang et al.

The Unbearable Slowness of Being: Why do we live at 10 bits/s?

by Jieyu Zheng et al.

Hidden in Plain Text: Emergence & Mitigation of Steganographic Collusion in LLMs

by Yohan Mathew et al.

Analyzing (In)Abilities of SAEs via Formal Languages

by Abhinav Menon et al.

MetaMorph: Multimodal Understanding and Generation via Instruction Tuning

by Shengbang Tong et al.