실시간
국내외 뉴스 · 기업 공식 발표 · 논문 · 영상 · 커뮤니티 소식을 한국시간 기준으로 제공합니다. 같은 소식은 하나로 묶고, 기본은 핵심만 보여 드립니다.
모든 수집 소식(구글 뉴스로 들어온 단건 보도 포함).
Autoregressive decoding relies on the KV cache, whose memory footprint grows linearly with context length and caps batch size and throughput.
Vision-language-action models are typically built on a simple premise: perception is first compressed by visual encoders, and action reasoning begins only…
We introduce LongBanana, to our knowledge the first expert-designed and expert-verified benchmark for long-context multi-reference image synthesis in the age…
Coding agents powered by models such as GPT-6-Astra connect spatial reasoning with executable robot behavior, raising the question of how such agents can…
Generative video models are increasingly used as visual world simulators, yet their primary strength lies in rendering plausible pixels rather than reasoning…
Prefill-to-Autoregressive Cross-model Transfer (PACT), a form of latent communication between language models, combines a larger model's prompt representations…
Offline retrieval-augmented generation (RAG) on edge devices is updated through signed knowledge packs that carry text and precomputed embedding vectors.
While multi-turn agentic reinforcement learning (RL) excels on long-horizon tasks, its performance gains remain highly sensitive to interaction constraints.
Streaming speech recognition is increasingly consumed by machines, such as translators and voice agents, that act on each token as it appears.
Universal image restoration aims to handle diverse degradations within a single model, but a reliable scaling strategy remains underexplored.
Streaming video-to-audio (V2A) generation is essential for immersive interactive applications.
Large language model (LLM) agents increasingly rely on external memory stores to retain information across conversations, typically via dense vector embeddings…
Few-step distillation offers efficient generation with diffusion and flow models, but preserving quality with only a few sampling steps remains challenging.
Omni models answer questions about videos by jointly processing sampled frames and audio in one turn, with progress driven largely by scaling model size and…
AI agents are playing an increasingly important role in physics research.
Streaming video understanding requires models to repeatedly decide whether to respond or continue observing.
Group Relative Policy Optimization (GRPO) has advanced generative model post-training in verifiable domains such as code and mathematics, but evaluating video…
Target-conditioned diffusion drafters predict candidate tokens in parallel, yet each new block must wait for updated target-model hidden states.
Egocentric human video offers a scalable source of manipulation priors for robot learning, yet translating raw data scale into generalizable robot policies…
World Action Models (WAMs) use the predictive knowledge of pretrained video diffusion models for robot control through future video prediction.
Strong single-turn editing performance does not guarantee reliable multi-turn interaction: as edited outputs are repeatedly reused, small unintended changes…
Chunk-interleaved full-duplex speech language models listen and speak in fixed time chunks, and each chunk must be processed before the next one arrives.
Large language model (LLM) agents typically append raw tool outputs to their context.
Financial backtests of large language models (LLMs) are meaningful only if the model did not already know the outcomes it is asked to predict.
A central yet under-explored question in Multimodal Large Language Models (MLLMs) is where to connect---how visual information from a hierarchical vision…
Mixture-of-Experts (MoE) enables multimodal large language models (MLLMs) to scale capacity efficiently, but expert parameters dominate memory even though only…
We introduce Micius-Flash, a 27-billion-parameter model for engineering with native multimodal input, deep reasoning and a 256K-token context window.
Adversarial diffusion distillation has conventionally relied on image features for discrimination.
Can a neural network learn to render 3D Gaussian splats on its own, with no rasterizer in the renderer?
For a decade, progress in artificial intelligence has been measured by how much a machine can do on its own.