大模型能力提升路线图：从"堆参数"到训练全栈 + 外层程序
把 2026 年可核查的公开证据整理成一张六层能力路线图——预训练、后训练 RL、推理时计算、上下文与记忆、智能体与 Harness、世界模型。含 Meta ScaleRL 40 万 GPU 小时实验结论、RL 预算占比 10%–30% 口径、Chinchilla 对比、Meta-Harness 6x 差距等数据锚点，并给出优先级表与算法工程师/产品经理的行动建议。
阅读全文 →
最新文章
LATEST 共 222 条Compile by Training: Turning Natural-Language Specifications into Local Neural Functions
Many recurring text functions are easy to describe but difficult to implement with rules, while calling a large remote m…
MaxKernel: Agentic Kernel Generation for TPUs
Designing and authoring high-performance custom kernels for accelerators is a complex task that requires deep hardware-l…
One Editor, Many Edits: A Unified Training-Free Framework for Diverse Video Editing
Video editing spans diverse editing paradigms, yet achieving high-quality instruction-guided and subject-guided editing …
ENEAS: Embedding-guided Neural Ensemble for Adaptive Segmentation
We present ENEAS, a unified, text-promptable method for instance tracking and semantic discovery. Text-promptable segmen…
AdaptVPR: Route-Aware Hard Positive Generation for Robust Visual Place Recognition
Visual Place Recognition (VPR) localizes a query image by retrieving database images of the same or nearby place, yet it…
Safety for Whom? Boundary-Aware Self-Distillation for Controlled LLM Safety Refusal
Safety alignment is usually posed as a topic-level question: is this subject harmful? Deployments ask a narrower one. A …
Unlocking Lossless Speedups in LLMs via Discrete Diffusion
Large Language Models (LLMs) owe much of their success to next-token prediction (NTP), but their autoregressive (AR) str…
Privacy Failure in Split-LLM Training, The Returned Gradient Nullifies the Decoys
We present a systems-security case study of a two-node split-LLM training system whose privacy evaluation passed while l…
What Else Needs Fixing? Exploring Cost-Effective Test-Time Compute for Revision Propagation in Artifacts Generated Through Conversation
Large Language Models (LLMs) often help users generate artifacts through iterative cycles of generation and revision in …
RoboTok: An Internet-Scale Data Engine for Human Demonstration Retrieval and Dexterous Manipulation Learning
Robot learning increasingly depends on broad and diverse demonstrations, yet collecting robot data remains expensive and…
Let Confidence Change, Not the Prediction: Prediction-Preserving Repair for Post-hoc Calibration
Post-hoc calibration corrects reported confidence, yet a multiclass calibrator can also change the associated top-1 pred…
A Common Measure of Communication for Speech Brain-Computer Interfaces
Speech brain-computer interfaces (speech BCIs) translate neural activity into language, offering a path towards restorin…