Archive
1536 technical news articles
推論系統
The new release stops overriding GPU memory information with the system’s `MemAvailable` value in Linux HIP builds and instead trusts `hipMemGetInfo`. The fix targets AMD APUs with configurable UMA carveouts and reduces the risk of the model loader overestimating capacity and failing later.
代理工具
PACE-Bench uses 144 executable physics environments to test whether agents can repair previously successful program designs that fail after changes to friction or material constraints. Experiments show that reflection outperforms unverified self-revision, while long-term memory can anchor stronger models to early solutions.
訓練基礎設施
Rollplex executes video encoding and prompt prefill for the reference model and training actor early, during autoregressive decoding, while preserving synchronous on-policy semantics. The system uses CUDA VMM to manage memory across stages and enables training and inference processes with different tensor-parallel configurations to share compatible weights.
CForce 沿用擴散語言模型自己的生成軌跡，把後期較完整的預測蒸餾回早期遮罩狀態。LLaDA2.1-mini 在提高平行解碼量的同時維持準確度，但證據目前集中於同一模型家族與作者控制的評測。
最新模型
sMuon first projects the orthogonalized full-weight update direction into the low-rank space expressible by LoRA factors, then computes the update using only matrix multiplications. In ReLoRA experiments, it matches Riemannion’s lowest validation loss, although cross-model fine-tuning results depend heavily on the optimizer originally used for the base model.
代理工具
ScienceFlow saves more than conversation summaries: it packages code, validation evidence, resource records, and workspace snapshots into recoverable stages. The official results report a 70.22% Any-Medal rate on the full MLE-bench, though cross-system comparisons remain affected by differences in models, hardware, and time budgets.
推論系統
The new release configures threads and work-groups according to quantization block size, preventing over- or undersubscription in the SYCL copy kernel. Microbenchmark throughput on Arc 70 rose from 20.21 to 158.19 GB/s, but this does not represent the speedup in token generation for a complete model.
最新模型
Intern-S2-Mobius separates the knowledge storage and attention-based reasoning traditionally tied to each Transformer layer, allowing multiple Reasoners to repeatedly query the same global Memory. The open weights can be loaded with LMDeploy, vLLM, or Transformers, but the nearly 4× acceleration remains a result from the official evaluation under specific conditions.
最新模型
The community has trained a 5.21GB single-frame VAE for the MiniMax H3 video model, allowing reference-to-video pipelines to generate just one frame for tasks such as virtual try-on, pose editing, and viewpoint transformation. The approach demonstrates how a video model can be repurposed as an image editor, but it currently depends on unofficial weights, specific workflows, and ComfyUI single-frame support that has yet to be fully implemented.
最新模型
Qwen has released the weights for Qwen3.8-27B, using a 64-layer hybrid Gated DeltaNet/Gated Attention architecture to reduce long-context costs while providing native visual understanding and adjustable reasoning depth. Official agent benchmarks show substantial gains, but some datasets, corrected tasks, and execution frameworks were configured by Qwen, so the results should not be treated as a fair cross-vendor ranking.
代理工具
The UK AI Security Institute has open-sourced optstop, which uses posterior uncertainty at the item and task levels to decide when to stop repeated evaluations. Across nine shadow tests, it saved an average of 81.1% of trials, though performance varied with score type, item ordering, and the exchangeability assumption.
推論系統
FreeBalance uses the previous layer’s residual state to predict expert load in the next layer, overlapping weight transfers with attention computation. The method does not alter the final routing decisions or model outputs, but the evidence so far covers only two MoE models, a single eight-GPU topology, and prefill workloads.