58 results on this page · clear filters

ai Sep 07 Speculative Decoding in vLLM on AMD GPUs vLLM has added support for speculative decoding on AMD GPUs, a technique that lets the serving system verify multiple drafted tokens in a single pass through the target model. The feature works across five different drafting metho... ai Sep 07 Nvidia's Jensen Huang says 'AGI has arrived' and congratulates OpenAI Nvidia CEO Jensen Huang declared on Sunday that artificial general intelligence has arrived, congratulating OpenAI on the release of Astra, the company's newest and most powerful model. The statement, posted on X, adds another voi... ai Sep 07 Same Trajectory, Contradictory Rewards (ROBORMBENCH): Paraphrase Fragility in Vision Language Reward Models Vision-language models are being adopted as reward functions for robotic learning at an accelerating pace. The idea is straightforward: feed a robot trajectory and a text description of the goal into a VLM, and the model outputs a... ai Sep 07 Necessary or Sufficient? Evaluating LLM Explanations With Behavioural Evidence When an LLM inside an agent workflow produces a recommendation or judgment, it often comes with an explanation naming the factors that drove the decision. Operators use these explanations to monitor systems, diagnose errors, or de... ai Sep 07 Molecular Déjà Vu: Digit-Level Retrieval of Published Values in Frontier Language Models When an LLM reports a molecular property with a median absolute error of 0.025 kcal/mol on the FreeSolv benchmark, that number is far below the 0.6 kcal/mol experimental uncertainty assigned to the measurements. No model can predi... ai Sep 07 When LLM Decompilers Recompile More and Preserve Less When LLM Decompilers Pass Every Test Yet Rewrite Your Code Decompilation turns compiled binaries back into readable source code, and the stakes are high: security analysts depend on it to find vulnerabilities in malware, reverse-e... programming languages Sep 07 Design Docs Are All You Need: An AI-native Machine-Learning Performance Tool ML Performance Tools Break Every Year. What If You Regenerated Them Instead of Maintaining Them? Machine-learning performance modeling sits at the worst possible intersection in computing. Above it, model architectures mutate mont... machine learning Sep 07 Distill Globally, Adapt Locally: Reasoning Distillation and Product-Type Test-Time Training for Scalable Trade-Up Recommendation How Amazon Trains a 15M-Parameter Model to Replace LLM Calls for Product Upgrade Recommendations E-commerce platforms need to recommend better products to customers, not just similar ones. A shopper buying a basic moisturizer shou...