←Search results

Search “Video”

By relevance · Total 2285 results Clear search

Wednesday

  2. Rohan Paul

    Meta's new paper proposes the ProPerMem benchmark: proactive assistants struggle with autonomously judging when to interrupt

    A new Meta paper points out that the failure point of proactive assistants (such as AI glasses) lies in autonomously judging when to speak, not just what to say. The team built the ProPerMem benchmark, using first-person video paired with interference-rich, full-year memory averaging 618K tokens, and featuring human-verified trigger windows. All baselines scored at most 15%, even frontier models using retrieval-augmented memory; when oracle evidence was provided within the window, GPT-5.3-Chat reached 96%, but when it was left to choose the timing itself, this dropped to 38%, and to 15% after adding retrieval. Grasping both content and timing while reducing trigger frequency can raise accuracy from under 10% to 42.4%.

    A new Meta paper points out that the failure point of proactive assistants (such as AI glasses) lies in autonomously judging when to speak, not just what to say. The team built the ProPerMem benchmark, using first-person video paired with interference-rich, full-year memory averaging 618K tokens, and featuring human-verified trigger windows. All baselines scored at most 15%, even frontier models using retrieval-augmented memory; when oracle evidence was provided within the window, GPT-5.3-Chat r

    Matched fieldsSummary、Body

    #ai-news#Papers/Research#Agents#Multimodal
  6. Hugging FaceSelected

    NVIDIA Releases Cosmos3-H-Dreams Surgical Generative Simulation Model

    NVIDIA has released Cosmos3-H-Dreams, specialized from the 16-billion-parameter Cosmos3-H-Embodied-Nano for action-conditioned video generation of cholecystectomy. The model is trained with 28 action dimensions, 832 x 480 video, and 10 Hz action alignment, and distillation yields two student checkpoints, four-step and two-step; the two-step version is trained separately, offering faster inference but lower image quality. NVIDIA also provides the FlashDreams streaming runtime and methods for adapting to custom data and controllers, and states that the model is a research simulator, not a validated clinical system.

    NVIDIA has released Cosmos3-H-Dreams, specialized from the 16-billion-parameter Cosmos3-H-Embodied-Nano for action-conditioned video generation of cholecystectomy. The model is trained with 28 action dimensions, 832 x 480 video, and 10 Hz action alignment, and distillation yields two student checkpoints, four-step and two-step; the two-step version is trained separately, offering faster inference but lower image quality. NVIDIA also provides the FlashDreams streaming runtime and methods for adap

    Matched fieldsSummary、Body

    #lab#Model releases#Video#Open-source ecosystem

Tuesday

  6. Shao Meng

    Stanford CME 295 Lecture 4 released: Teaching reinforcement learning with LLMs

    The Stanford course CME 295 Transformers & Large Language Models has been updated to Lecture 4, Reinforcement learning with LLMs, and both the video and lecture notes are now public. This lecture goes from RL and Reward Design to PPO, GRPO, RLVR, and DAPO, explaining the notation in each one by one. The course is taught by Afshine and Shervine Amidi, with 9 lectures in total, covering Transformer architecture, attention variants, RoPE, LoRA fine-tuning, RLHF/GRPO training, Flash Attention inference optimization, MCP and AI Agents, and diffusion language models.

    The Stanford course CME 295 Transformers & Large Language Models has been updated to Lecture 4, Reinforcement learning with LLMs, and both the video and lecture notes are now public. This lecture goes from RL and Reward Design to PPO, GRPO, RLVR, and DAPO, explaining the notation in each one by one. The course is taught by Afshine and Shervine Amidi, with 9 lectures in total, covering Transformer architecture, attention variants, RoPE, LoRA fine-tuning, RLHF/GRPO training, Flash Attention infere

    Matched fieldsSummary

    #hot-signal#Tutorials / practice#Reasoning#English text is being prepared.
  13. Hugging FaceSelected

    PyTorch 2.15 Brings FP8 and Faster MoE Decoding to MPS

    PyTorch 2.15 adds FP8 support to the MPS backend and makes MoE model decoding 5–6.5 times faster than 2.14: on an M3 Ultra with torch.compile, Qwen3.6-35B-A3B goes from 9.4 tokens/s to 61.3 tokens/s, and LFM2.5-8B-A1B goes from 23.6 to 123.6 tokens/s. For Wan2.2's tiled VAE video decoding, peak driver memory drops from about 270 GiB to 8 GiB, and the image corruption issue with Qwen-Image-2.1's VAE encoding on MPS is also fixed with a padding change, raising the encode-decode round-trip PSNR from 10.06 dB to 29.95 dB. This version requires macOS 15 or later and Python 3.11 or later.

    PyTorch 2.15 adds FP8 support to the MPS backend and makes MoE model decoding 5–6.5 times faster than 2.14: on an M3 Ultra with torch.compile, Qwen3.6-35B-A3B goes from 9.4 tokens/s to 61.3 tokens/s, and LFM2.5-8B-A1B goes from 23.6 to 123.6 tokens/s. For Wan2.2's tiled VAE video decoding, peak driver memory drops from about 270 GiB to 8 GiB, and the image corruption issue with Qwen-Image-2.1's VAE encoding on MPS is also fixed with a padding change, raising the encode-decode round-trip PSNR fro

    Matched fieldsSummary、Body

    #lab#Product updates#English text is being prepared.#Open-source ecosystem