MAROKO133 Breaking ai: RFK Jr Startled by Trump’s Ability to Remain Alive Despite Dumpster

📌 MAROKO133 Update ai: RFK Jr Startled by Trump’s Ability to Remain Alive Despite

Much ink has been spilled over US health secretary Robert F. Kennedy Jr.’s dalliances with anti-vaccine conspiracy theories, brain worms, nicotine pouches, and bizarre self-treatment with a synthetic dye known as methylene blue.

In spite of all those wellness eccentricities of his own, Kennedy is apparently in awe of his boss Donald Trump, who he says spends his days “pumping himself full of poison.”

In a recent appearance on the Katie Miller Podcast — hosted by the wife of Stephen Miller, who currently serves as homeland security advisor to the White House — Kennedy expressed astonishment that the president is even alive.

“He eats really bad food,” the health secretary dished. “Which is McDonald’s, and, you know, candy and Diet Coke. But he drinks Diet Coke at all times. He has the constitution of a deity — I don’t know how he’s alive, but he is.”

Though Kennedy acknowledged that Trump eats “really good food” when he’s staying in a place like Mar-a-Lago, he says those habits fall away the second he gets on the road.

“If you travel with him you get this idea that he’s just pumping himself full of poison all day,” Kennedy told Miller. “He wants to eat food from big corporations because he trusts it and he doesn’t want to get sick when he’s on the road.”

Trump’s health woes have been a topic of heated debate since he assumed his second term in office. He’s currently the oldest person to be elected president in US history, a superlative which has come with complications like daytime fatigue, visible bruising, and what his critics say is observable cognitive decline. (A mysterious CT scan that the president has struggled to explain hasn’t helped dispel those concerns.)

Whether Trump’s diet is contributing to his health woes is hard to say for certain — the administration insists he remains perfectly fit — but if Kennedy’s astonishment is any indication, the BigMacs certainly aren’t helping.

More on RFK: The “Sober” RFK Jr. Has Allegedly Been Smoking DMT

The post RFK Jr Startled by Trump’s Ability to Remain Alive Despite Dumpster-Tier Diet appeared first on Futurism.

🔗 Sumber: futurism.com

📌 MAROKO133 Hot ai: Adobe Research Unlocking Long-Term Memory in Video World Model

Video world models, which predict future frames conditioned on actions, hold immense promise for artificial intelligence, enabling agents to plan and reason in dynamic environments. Recent advancements, particularly with video diffusion models, have shown impressive capabilities in generating realistic future sequences. However, a significant bottleneck remains: maintaining long-term memory. Current models struggle to remember events and states from far in the past due to the high computational cost associated with processing extended sequences using traditional attention layers. This limits their ability to perform complex tasks requiring sustained understanding of a scene.

A new paper, “Long-Context State-Space Video World Models” by researchers from Stanford University, Princeton University, and Adobe Research, proposes an innovative solution to this challenge. They introduce a novel architecture that leverages State-Space Models (SSMs) to extend temporal memory without sacrificing computational efficiency.

The core problem lies in the quadratic computational complexity of attention mechanisms with respect to sequence length. As the video context grows, the resources required for attention layers explode, making long-term memory impractical for real-world applications. This means that after a certain number of frames, the model effectively “forgets” earlier events, hindering its performance on tasks that demand long-range coherence or reasoning over extended periods.

The authors’ key insight is to leverage the inherent strengths of State-Space Models (SSMs) for causal sequence modeling. Unlike previous attempts that retrofitted SSMs for non-causal vision tasks, this work fully exploits their advantages in processing sequences efficiently.

The proposed Long-Context State-Space Video World Model (LSSVWM) incorporates several crucial design choices:

1. Block-wise SSM Scanning Scheme: This is central to their design. Instead of processing the entire video sequence with a single SSM scan, they employ a block-wise scheme. This strategically trades off some spatial consistency (within a block) for significantly extended temporal memory. By breaking down the long sequence into manageable blocks, they can maintain a compressed “state” that carries information across blocks, effectively extending the model’s memory horizon.
2. Dense Local Attention: To compensate for the potential loss of spatial coherence introduced by the block-wise SSM scanning, the model incorporates dense local attention. This ensures that consecutive frames within and across blocks maintain strong relationships, preserving the fine-grained details and consistency necessary for realistic video generation. This dual approach of global (SSM) and local (attention) processing allows them to achieve both long-term memory and local fidelity.

The paper also introduces two key training strategies to further improve long-context performance:

• Diffusion Forcing: This technique encourages the model to generate frames conditioned on a prefix of the input, effectively forcing it to learn to maintain consistency over longer durations. By sometimes not sampling a prefix and keeping all tokens noised, the training becomes equivalent to diffusion forcing, which is highlighted as a special case of long-context training where the prefix length is zero. This pushes the model to generate coherent sequences even from minimal initial context.
• Frame Local Attention: For faster training and sampling, the authors implemented a “frame local attention” mechanism. This utilizes FlexAttention to achieve significant speedups compared to a fully causal mask. By grouping frames into chunks (e.g., chunks of 5 with a frame window size of 10), frames within a chunk maintain bidirectionality while also attending to frames in the previous chunk. This allows for an effective receptive field while optimizing computational load.

The researchers evaluated their LSSVWM on challenging datasets, including Memory Maze and Minecraft, which are specifically designed to test long-term memory capabilities through spatial retrieval and reasoning tasks.

The experiments demonstrate that their approach substantially surpasses baselines in preserving long-range memory. Qualitative results, as shown in supplementary figures (e.g., S1, S2, S3), illustrate that LSSVWM can generate more coherent and accurate sequences over extended periods compared to models relying solely on causal attention or even Mamba2 without frame local attention. For instance, on reasoning tasks for the maze dataset, their model maintains better consistency and accuracy over long horizons. Similarly, for retrieval tasks, LSSVWM shows improved ability to recall and utilize information from distant past frames. Crucially, these improvements are achieved while maintaining practical inference speeds, making the models suitable for interactive applications.

The Paper Long-Context State-Space Video World Models is on arXiv

The post Adobe Research Unlocking Long-Term Memory in Video World Models with State-Space Models first appeared on Synced.

🔗 Sumber: syncedreview.com