GitHub Repo

GitHub 熱門專案、開源工具、框架、runtime 與重要 release。

TS-RAG Fuses Historical Sequences via Reference Tokens, Reducing Average MSE to 0.310 Across Six Forecasting Datasets

Baidu researchers have adapted RAG from text generation to multivariate time-series forecasting, using a TCN to retrieve similar segments and cross-attention to fuse them. A channel-dependent variant outperformed the listed baselines across six datasets, but the code has not been released, and maintainers have warned that the conventional benchmarks used may no longer be sufficiently discriminative.

2026-08-09

Vision Models Can Zoom In on Images Without Necessarily Using the Evidence; Qwen3-VL-8B’s Net Gain Is Just 6.9 Percentage Points

A new study uses counterfactual cropping to test six open models, distinguishing between “calling a tool” and “the tool’s returned content actually changing the answer.” Most positive gains are concentrated in a small number of well-calibrated trajectories, suggesting that final accuracy alone may overstate visual tool capabilities.

2026-08-07

代理工具

EnvACE Lets Agents Role-Play Their Own Tool Environments; Qwen3-8B Averages 32.91% Across Three Benchmarks

During training, EnvACE does not query external environments. Instead, the same policy alternates between generating tool actions and imagined environment responses. This reduces reliance on executable training environments, but also directly absorbs simulation errors into the agent’s parameters.

2026-08-07

DASH Dynamically Allocates Distillation Weights Based on Reasoning Divergence, Raising Qwen3-1.7B’s Math Average by 3.2 Points

Rather than treating teacher–student differences at every token equally, DASH adjusts the scope of supervision based on how divergence changes across an entire reasoning sequence. All three Qwen3 sizes outperform OPSD under the same conditions, but selecting the best checkpoint by average test-benchmark score may overestimate generalization gains.

2026-08-09

硬體

MicroEvo Uses LLMs and MCTS for Processor Design, Requiring 10.6× Fewer Simulations Than NSGA-II to Reach the Target

MicroEvo combines processor-design knowledge, Pareto tree search, and historical PPA feedback to find performance, power, and area trade-offs with fewer simulations. Its maximum hypervolume gain of 36.2% comes from a simulated design space and should not be equated with improvements in physical silicon.

2026-08-07

推論系統

PaDoc Parses Documents in Parallel with Layout Branches, Boosting Throughput by Up to 118% on a Single A800

PaDoc decodes the layout sequence and each region’s content in parallel while sharing the page prefix, avoiding serialization of the entire document into a single path. Its 2.1B model maintains a 94.24 Overall score on OmniDocBench, though the performance figures come from a single GPU under specific scheduling settings.

2026-08-07

3D 生成與具身 AI

iARCS Uses LLMs to Generate Reward Programs for 3D Scenes, Reducing the Object Collision Rate from 52.67% to 40.45%

iARCS first corrects collisions and walkability issues in an indoor scene generator, then compiles natural-language requirements into executable reward functions for a second stage of reinforcement learning. In 3D-FRONT experiments, it outperforms MiDiffusion on geometric metrics, but each new requirement requires a separately trained LoRA, and the authors have not yet released an implementation.

2026-08-09

硬體

esp32-ai Fits a 28.9M-Parameter Model on the ESP32-S3, Reaching 9.88 Tokens/s Offline

The open-source esp32-ai project uses 4-bit quantization and tiered memory allocation to keep roughly 25 million embedding parameters in flash, reading only the rows needed for each token. The model can generate text offline on a microcontroller costing under $10, though its capabilities remain limited to short stories and single-domain question answering.

2026-07-26

推論系統

PhyAI Unifies Inference for VLAs and World-Action Models, Delivering 1.40× to 4.65× Speedups over Official Implementations

PhyAI uses model adapters to preserve each architecture’s conditioning, solver, and action semantics while sharing graph execution, kernels, caching, and multi-GPU serving. Public benchmarks cover π0, π0.5, GR00T N1.7, Cosmos3, and MiniCPM-Robot, although some comparisons do not use exactly the same numerical precision.

2026-08-06

代理工具

TutorMoments Replays Real Tutoring Decisions, Finds Seven LLMs Default to Over-Scaffolding

Ai2 built a replayable evaluation from 462 real math tutoring transcripts, asking models to choose between providing scaffolding and requiring deeper student reasoning. Explicitly prompting for this tradeoff improves the performance of all seven models, but simulated students and model-based grading still cannot demonstrate real learning outcomes.

2026-08-09

應用研究

Otter Predicts Human Decisions Using Move History and Time Controls; 15.3M-Parameter Model Reports 55.23% Top-1 Accuracy

Rather than treating each board position as an independent sample, Otter incorporates the previous 20 moves and time-control information. The model outperformed Maia-2 on the authors’ Lichess rapid test, but was not directly compared with the published Maia-3 using the same data split.

2026-08-08

代理工具

SMRC-SD Verifies Agent State Before Distilling Successful Trajectories, Improving Qwen3-1.7B Task Success Rate by About 12 Percentage Points

Successful demonstrations may not apply to states reached after an agent takes a detour, and unconditionally providing the full trajectory can even reduce the probability of the correct action. SMRC-SD adds a self-distillation signal only when the state is compatible with a demonstration step, outperforming the full-path baseline on both ALFWorld and WebShop.

2026-08-08