Kepler Computing claims a new approach to chip design--and a proprietary material--can help end the supply bottlenecks that have sent memory prices surging. An ambitious chip startup that has spent more than seven years quietly trying to redesign the architecture for computer memory has just come out of stealth mode and believes its new approach can help ease the global memory-chip shortage --provided it can produce its technology at scale. Kepler Computing, a San Jose, California-based startup founded in 2018 by a team of physicists and computer scientists, says it has developed a new architecture for high-bandwidth memory (HBM) that directly addresses some of the chip supply bottlenecks that are constraining the computing market. While chipmakers typically rely on expensive extreme ultraviolet lithography (EUV) to shrink the transistors on a chip, thereby packing more technology into the same amount of space, Kepler claims that its "3D stacking" approach and a proprietary new material allow it to increase density without relying on EUV at all--and it can work with existing semiconductor fabrication plants. Kepler says it has made similar gains for the high-speed cache memory typically used in CPUs, GPUs, and XPUs.

The Chinese company is adapting to the demise of Moore's Law, which guides chip production. It could complicate US chip dominance. Tingbo He, president of Huawei's chip-design subsidiary HiSilicon, says her company's engineers have developed a novel way to optimize semiconductors--and she believes it will close the performance gap between Chinese and Western chips over the next few years. Huawei's method, in short, focuses on speeding up computations across chips, circuits, and entire computing systems, rather than squeezing ever-more components onto a single piece of silicon. "We found a new path," He said at the IEEE International Symposium on Circuits and Systems in Shanghai last weekend.

We introduce Bootstrap Your Own Latent (BYOL), a new approach to self-supervised image representation learning. BYOL relies on two neural networks, referred to as online and target networks, that interact and learn from each other. From an augmented view of an image, we train the online network to predict the target network representation of the same image under a different augmented view. At the same time, we update the target network with a slow-moving average of the online network. While state-of-the art methods intrinsically rely on negative pairs, BYOL achieves a new state of the art without them. BYOL reaches 74.3% top-1 classification accuracy on ImageNet using the standard linear evaluation protocol with a standard ResNet-50 architecture and 79.6% with a larger ResNet. We also show that BYOL performs on par or better than the current state of the art on both transfer and semi-supervised benchmarks.

Continual learning agents experience a stream of (related) tasks. The main challenge is that the agent must not forget previous tasks and also adapt to novel tasks in the stream. We are interested in the intersection of two recent continual-learning scenarios. In meta-continual learning, the model is pre-trained using meta-learning to minimize catastrophic forgetting of previous tasks. In continual-meta learning, the aim is to train agents for faster remembering of previous tasks through adaptation.

Reward shaping is an effective technique for incorporating domain knowledge into reinforcement learning (RL). Existing approaches such as potential-based reward shaping normally make full use of a given shaping reward function. However, since the transformation of human knowledge into numeric reward values is often imperfect due to reasons such as human cognitive bias, completely utilizing the shaping reward function may fail to improve the performance of RL algorithms. In this paper, we consider the problem of adaptively utilizing a given shaping reward function. We formulate the utilization of shaping rewards as a bi-level optimization problem, where the lower level is to optimize policy using the shaping rewards and the upper level is to optimize a parameterized shaping weight function for true reward maximization. We formally derive the gradient of the expected true reward with respect to the shaping weight function parameters and accordingly propose three learning algorithms based on different assumptions. Experiments in sparse-reward cartpole and MuJoCo environments show that our algorithms can fully exploit beneficial shaping rewards, and meanwhile ignore unbeneficial shaping rewards or even transform them into beneficial ones.

The challenge of separating AI-generated text from human-authored content is becoming more urgent as generative AI technologies like ChatGPT become more widely available. In this work, we address this issue by looking at both the detection of content that has been entirely generated by AI and the identification of human text that has been reworded by AI. In our work, a comprehensive methodology to detect AI- generated text using XLM-RoBERTa, a state-of-the-art multilingual transformer model. Our approach includes rigorous preprocessing, and feature extraction involving perplexity, semantic, and readability features. We fine-tuned the XLM-RoBERTa model on a balanced dataset of human and AI-generated texts and evaluated its performance. The model demonstrated high accuracy and robust performance across various text genres. Additionally, we conducted feature analysis to understand the model's decision-making process, revealing that perplexity and attention-based features are critical in differentiating between human and AI-generated texts. Our findings offer a valuable tool for maintaining academic integrity and contribute to the broader field of AI ethics by promoting transparency and accountability in AI systems. Future research directions include exploring other advanced models and expanding the dataset to enhance the model's generalizability.

A startup hopes to challenge Nvidia, AMD, and Intel with a chip that wrangles probabilities rather than ones and zeros. Extropic claims its exotic new chip, called XTR-0, could be thousands of times more energy efficient than existing chips when scaled up. Extropic, a startup developing an exotic new kind of computer chip that handles probabilistic bits, has produced its first working hardware along with proof that more advanced systems will tackle useful tasks in artificial intelligence and scientific research. The startup's chips work in a fundamentally different way to chips from Nvidia, AMD, and others, and promise to be thousands of times more energy efficient when scaled up. With AI companies pouring billions of dollars into building datacenters, a completely new approach could offer a far less costly alternative to vast arrays of conventional chips.

In Indiana, Exploration Acres found a way to keep the family farm alive. Exploration Acres has operated its award-winning corn maze for almost 20 years. Breakthroughs, discoveries, and DIY tips sent every weekday. The adage refers to a farmer's goal for their crops if they hope to make the October harvest. And while most Midwesterners are familiar with the axiom, Tim Fitzgerald knows the folksy refrain lost its relevancy decades ago.

Is any special feature operation applied in ETN? & Does a larger K help? The motivation to compute affinity matrices & How to achieve the error diffusion. Please see Figure 1 in submission for example. Performance issues, including increased training burden and running time. Thanks for pointing out the mistake in real-time stylization, which will be corrected in revision.

Test-time scaling offers a promising path to improve LLM reasoning by utilizing more compute at inference time; however, the true promise of this paradigm lies in extrapolation (i.e., improvement in performance on hard problems as LLMs keep "thinking" for longer, beyond the maximum token budget they were trained on). Surprisingly, we find that most existing reasoning models do not extrapolate well. We show that one way to enable extrapolation is by training the LLM to perform in-context exploration: training the LLM to effectively spend its test time budget by chaining operations (such as generation, verification, refinement, etc.), or testing multiple hypotheses before it commits to an answer. To enable in-context exploration, we identify three key ingredients as part of our recipe e3: (1) chaining skills that the base LLM has asymmetric competence in, e.g., chaining verification (easy) with generation (hard), as a way to implement in-context search; (2) leveraging "negative" gradients from incorrect traces to amplify exploration during RL, resulting in longer search traces that chains additional asymmetries; and (3) coupling task difficulty with training token budget during training via a specifically-designed curriculum to structure in-context exploration. Our recipe e3 produces the best known 1.7B model according to AIME'25 and HMMT'25 scores, and extrapolates to 2x the training token budget. Our e3-1.7B model not only attains high pass@1 scores, but also improves pass@k over the base model.