def _purge(*prefixes):
for name in [m for m in list(sys.modules)
if any(m == p or m.startswith(p + ".") for p in prefixes)]:
del sys.modules[name]
def _load_ocrmypdf():
_purge("PIL", "ocrmypdf")
import…
Datalab has released lift, a 9B open-weights vision model for structured extraction. You pass it a JSON schema, and it returns a JSON object that matches. The model reads PDFs and images directly, then decodes against your schema.
This is Datalab’s first model built purely for extraction. The team already ships open-source OCR tools: chandra,…
Zyphra has released Zamba2-VL, a family of open vision-language models. The release covers three sizes: 1.2B, 2.7B, and 7B parameters. Each model is built on the Zamba2 hybrid SSM–Transformer backbone.
Vision-language models (VLMs) read images and text together. They answer questions about charts, documents, and photos. Most open VLMs use a dense Transformer as…
In this tutorial, we work through an end-to-end workflow for Qualcomm AI Hub Models. We start by setting up the required package, discovering the available model collection, and loading MobileNet-V2 for local PyTorch inference. We also handle an important input-shape issue by converting NHWC image tensors into the NCHW format expected by the model. From…
Liquid AI just released LFM2.5-VL-450M, an updated version of its earlier LFM2-VL-450M vision-language model. The new release introduces bounding box prediction, improved instruction following, expanded multilingual understanding, and function calling support — all within a 450M-parameter footprint designed to run directly on edge hardware ranging from embedded AI modules like NVIDIA Jetson Orin, to mini-PC…
For years, the computer vision community has operated on two separate tracks: generative models (which produce images) and discriminative models (which understand them). The assumption was straightforward — models good at making pictures aren’t necessarily good at reading them. A new paper from Google, titled “Image Generators are Generalist Vision Learners” (arXiv:2604.20329), published April 22,…
If you’ve ever watched a motion capture system struggle with a person’s fingers, or seen a segmentation model fail to distinguish teeth from gums, you already understand why human-centric computer vision is hard. Humans are not just objects, they come with articulated structure, fine surface details, and enormous variation in pose, clothing, lighting, and ethnicity.…
import random, numpy as np, torch, torch.nn as nn, torch.nn.functional as F
import matplotlib.pyplot as plt
from dataclasses import dataclass
from typing import Tuple, Dict, List
from torch.utils.data import Dataset, DataLoader
try:
from tqdm.auto import tqdm
except Exception:
def tqdm(x, **kwargs): return x
SEED = 7
random.seed(SEED); np.random.seed(SEED); torch.manual_seed(SEED)
if device.type == "cuda":
torch.backends.cudnn.benchmark = True
@dataclass
class WorldConfig:
…
Video foundation models can paint a beautiful frame. They are still notoriously bad at remembering it. Push the camera through a corridor in Wan 2.1 or CogVideoX and walls warp, objects morph, and details vanish — the giveaway that these models are fitting 2D pixel correlations rather than simulating a coherent 3D scene.
A team…
The open-source AI landscape has a new entry worth paying attention to. The Qwen team at Alibaba has released Qwen3.6-35B-A3B, the first open-weight model from the Qwen3.6 generation, and it is making a compelling argument that parameter efficiency matters far more than raw model size. With 35 billion total parameters but only 3 billion activated…