Explore tools, prompts, skills, news and resources related to AI 第20页.
Prompt works related to AI 第20页
Latest articles, prompts, use cases and editorial content about AI 第20页
Researchers introduce MuSeToM, a human-validated text-based benchmark for evaluating epistemic belief revision in Theory of Mind reasoning. It contains 2,415 instances adapted from BigToM and OpenToM, with textual cues s...
The paper targets batch makespan for LLM agent tasks that alternate between inference and environment interaction, a pattern common in benchmark evaluation, synthetic-data generation and RL rollouts. It introduces a work...
The paper introduces InertiaMPDD, a multimodal depression screening method that models emotional inertia by learning healthy next-state patterns with a world-model-inspired latent predictor. It derives reference-derived...
This paper identifies 'over-realization' in text-to-image generation, where a prompt-mentioned target appears in ways the prompt did not request, such as under negation, in imagined or believed content, in figu...
Google DeepMind released Gemini 4 Hydrogen, a closed-weights model for coding and agentic workflows with a 1,048,576-token unified context window and four thinking levels. According to Google, it scores 51 on the Artific...
Google Cloud has released TPU Sync, an Apache-2.0 C++ library that moves KV caches and model weights across TPU HBM, pinned host DRAM, shared storage, and data-center networking. It integrates with PyTorch and JAX and se...
Researchers introduce two-channel constrained GRPO to enforce safety budgets on harmful assistance and over-refusal in vision-language models. The method addresses two failure modes: scorer mean bias in the Lagrange mult...
Folio is a context manager for long-horizon language agents that records linked turn notes, runtime event manifests, and source records, then folds older history into coarser views. Its fold exposes handles into the mani...
Researchers evaluate a pose encoder trained with metric learning on American Sign Language, kept frozen, on six low-resource sign language dictionary datasets. With one enrolled clip per sign, the encoder ranks the corre...
Researchers introduce AstroMemBench, a benchmark for evaluating long-term memory systems in embodied spacecraft agents operating under communication delays, resource limits and safety constraints. The benchmark uses a Sc...
Researchers asked three large language models to independently reprove all 465 propositions of Euclid's Elements and compared their citation choices with human proofs using Jaccard similarity and network analysis. A...
This arXiv paper investigates when and how delegation improves LLM performance in agentic systems. Using purpose-built datasets with pre- and post-cutoff splits, the authors compare delegation modes and find no consisten...
ZONOS3-Mini is an ultra-compact, real-time zero-shot voice-cloning TTS model designed to run on laptops or smartphones. It uses a latent mixture-of-experts backbone with 886M parameters (100M active per token) and a new...
RESYNC addresses high-rate streaming inference where a large model may miss per-observation deadlines. The large model runs asynchronously while a fast path updates its stale latent state using newer observations and reu...
Researchers present PISim, a simulator that couples pretrained deep neural network execution with physics-based models of photonic accelerator architectures, modulator technologies, optical source organizations, and read...