Archive
新模型、開放權重、多模態、語音、影像與模型架構。
代理工具
SkillGate finds that when long-horizon agents are trained with outcome rewards, the small number of tokens used to select a skill receive almost no effective credit. The new method separates two gradient channels within the same GRPO update and outperforms the outcome-reward baseline across five agent benchmarks.
代理工具
A new framework uses predictive entropy to determine whether an LLM judge should accept a verdict directly, search for web evidence, or abstain, while calibrating two thresholds with a Clopper–Pearson upper bound. All 32 open-domain question-answering experiments maintained the specified error rate, but the guarantee depends on i.i.d. calibration data and reliable labels.
推論系統
Google DeepMind proposes mixing the deep residual stream from one token into shallow layers for subsequent tokens at inference time, creating cross-token recurrence in off-the-shelf Gemma 3 models. The method adds no model weights, but turns parallel prefill into sequential processing, and its real-world latency has yet to be fully measured.
資訊檢索／RAG
DEPT uses the same decoder to generate query expansions and encode documents, while a preservation loss prevents the existing vector index from drifting during fine-tuning. It outperformed staged baselines on five BEIR benchmarks, although the results are still based on single runs with two small models.
最新模型
Rather than modifying or distilling models, OYS uses Bayesian optimization to find a low-step denoising schedule for each model and task. The study reports improvements across six text-to-image models and an inpainting task, but the search cost must be amortized over a large volume of generated samples.
代理工具
The Alibaba Cloud team integrates browser-agent error recovery, complex UI interaction, and long-horizon credit assignment into a unified training pipeline. Its 27B model achieves 65.1% Pass@1 on the newly created bilingual Chinese-English BrowserBench, though the public availability of the model weights and evaluation data remains to be confirmed.
推論系統
Qwen3.8-27B 讓 27B 級模型進入單張 24GB 消費級 GPU 的可用範圍。公開資料顯示，一般 GGUF 部署約落在 30 至 60 tok/s；在 RTX 4090 上啟用 KV cache 量化、MTP 與新版 llama.cpp 後，社群實測可提升至 70 至 85 tok/s，但這仍不是開箱即得的基準。
推論系統
The IOL-AI Challenge requires systems to infer the rules of an unfamiliar language from a small number of examples before completing translation, transcription, and correction tasks. Under a single-T4 constraint, the best submission raised the same model’s baseline GM score from 9.40 to 19.79, but still lagged well behind closed models that reached the gold-medal threshold.
AI 安全
PACE does not ask language models to determine whether transactions are safe. Instead, it uses deterministic rules to check transaction intent, simulation results, and actual calldata. A smart account revalidates the signed policy decision record before execution, though the zero-failure result so far comes only from a simplified DeFi sandbox.
AI 安全
Google DeepMind researchers had the same Gemini policy play both solver and critic, with a weaker frozen model serving as judge. Debate preserved the judge’s discriminative ability and recovered about 45% of the gap to RLVR, at the cost of more training steps and constrained critique length.
推論系統
NVIDIA has open-sourced TensorRT Model Connect, which uses two commands to turn supported Hugging Face or local checkpoints into versioned bundles that can be handed off to C++ applications. It shortens the model-porting path, but remains a reference implementation; support and performance must be validated for each model, precision, and hardware configuration.
硬體
PTXBench checks whether generated kernels are correct, whether specified instructions actually execute, and how their performance compares with cuBLAS, cuDNN, and FlashInfer. The results show that generating instructions for new architectures does not necessarily translate into effective acceleration, with B200 attention kernels proving especially difficult.