Intuit

American software giant Intuit becomes S&P 500’s worst performer this year

American software giant Intuit has become the worst-performing stock in the S&P 500 this year, as investors worry that a new wave of AI-powered tax services could challenge the company's flagship TurboTax business. The company’s stock has fallen about 51% so far in 2026, even as CEO Sasan Goodarzi continues to defend the company's AI-focused strategy, saying during Intuit's third-quarter 2026 earnings call that the company had made a major bet on artificial intelligence. "When it comes down...

Can Vision Language Models Learn Intuitive Physics from Interaction?

Announce Type: replace Abstract: Pre-trained vision language models do not have good intuitions about the physical world. Recent work has shown that supervised fine-tuning can improve model performance on simple physical tasks. However, fine-tuned models do not appear to learn robust physical rules that can generalize to new contexts.

Do Video Foundation Models Understand Intuitive Physics? A Layerwise Probing Analysis

arXiv:2606.09646v1 Announce Type: new Abstract: We study whether pretrained video foundation models encode intuitive-physics information in their frozen representations, and how this information varies across model families, layers, and probe types. Using frozen-feature probing on IntPhys2 and Minimal Video Pairs (MVP), we compare predictive joint-embedding models (V-JEPA), masked reconstruction models (VideoMAE), and a diffusion-based video generator (LTX-Video). V-JEPA achieves the...

Variational Learning of Physical Intuition from a Few Observations

arXiv:2508.19537v4 Announce Type: replace Abstract: Humans often predict physical outcomes from only a few observations, a capability known as physical intuition. The mechanisms underlying this efficient learning remain elusive. Here, we introduce a variational learning framework in which small neural networks learn the mapping from observational parameters to optimal physical states from merely two or three similar examples.

IMWM: Intuition Models Complement World Models for Latent Planning

arXiv:2606.01626v1 Announce Type: new Abstract: Planning with a learned latent world model is a promising route to control from raw pixels, but a strong world model alone is not enough. We show this experimentally: even with a perfect world model (operationalized by replacing the learned forward predictor with an idealized rollout of the true environment dynamics), a finite-budget sample-based planner still fails on some tasks, indicating that the bottleneck can lie in search rather than in...

Riscrithm – An intuitive RISC-V assembler and optimizer coded in Go

MedSynapse-V: Bridging Visual Perception and Clinical Intuition via Latent Memory Evolution

arXiv:2604.26283v3 Announce Type: replace Abstract: High-precision medical diagnosis relies not only on static imaging features but also on the implicit diagnostic memory experts instantly invoke during image interpretation. We pinpoint a fundamental cognitive misalignment in medical VLMs caused by discrete tokenization, leading to quantization loss, long-range information dissipation, and missing case-adaptive expertise. To bridge this gap, we propose ours, a framework for latent diagnostic...

When Does Complexity Conditioning Help a Frozen Sentence Embedding? A Controlled Study of Per-Sentence and Pair-Level Difficulty Adaptation

Announce Type: new Abstract: A common intuition is that sentence embeddings should adapt to the difficulty of the input. We test this intuition in a controlled, multi-seed setting: a lightweight post-encoder adapter attaches to a frozen Qwen3-Embedding-0.6B encoder, accessing only its final pooled embedding, and is evaluated on four paraphrase and semantic-similarity tasks (PAWS, MRPC, QQP, STS-B). The naive form of the idea fails: surface-based per-sentence complexity is nearly uncorrelated...

The Frame Problem

The Frame Problem To most AI researchers, the frame problem is the challenge of representing the effects of action in logic without having to represent explicitly a large number of intuitively obvious non-effects. But to many philosophers, the AI researchers' frame problem is suggestive of wider epistemological issues. Is it possible, in principle, to limit the scope of the reasoning required to derive the consequences of an action?

Acquiring Human-Like Data-Efficient Mechanics Prediction from Deep Reinforcement Learning

Announce Type: replace Abstract: Humans can infer mechanical outcomes by learning from a few observations. This capacity for mechanics intuition is acquired in a data-efficient manner. Here, we propose a reinforcement learning framework to mimic this process, in which an agent encodes continuous physical observation parameters into its state and is trained via episodic switching across closely related observations.