GitHub Repo

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

WIDE Dynamically Prunes Attention and FFNs for Every Token, Accelerating End-to-End LLM Decoding by 1.55×

WIDE brings dynamic pruning down to token-level attention-head groups and FFN channel groups, supporting both prefill and decode. At 50% sparsity, the study reports up to a 4.95× decoding speedup for core layers, but the end-to-end gain falls to 1.55×.

2026-07-31

AI 安全

OWASP Agentic Skills Top 10 Completes Public Review for v1, Treating the Skill Supply Chain as a Distinct Attack Surface

The public review of the OWASP Agentic Skills Top 10 v1 draft has concluded. The framework organizes malicious skills, excessive permissions, dependency confusion, and cross-platform portability risks into ten control categories. It treats skills as the behavioral layer between models and MCP tools and proposes a universal format for declaring permissions, provenance, and integrity.

2026-08-02

POCKET Compresses a 35B Sparse MoE to 8.2 GB, Runs on Phones and CPU-Only Systems With Standard llama.cpp

VIDRAFT has released the weights for its POCKET series, quantizing a 35B model down to as little as 8.2 GB while retaining roughly 3B active parameters per token. The models run directly with upstream llama.cpp, although the compression method remains undisclosed and current performance and quality evidence comes primarily from the development team.

2026-08-02

ReToken Filters the Visual KV Cache With a Single Learnable Token, Improving Long-Video QA by 8.0 Points

Rather than feeding all image tokens into the model at once, ReToken retrieves sparse, question-relevant blocks from a prefilled visual KV cache. Its frozen-backbone approach trains only the retrieval token and fits on a single H100, although the results still come mainly from two 8B models.

2026-08-02

基準與基礎設施

MLPerf Endpoints v0.7 Launches, Adding Continuous Submissions and a Comparable Results Pipeline for Agentic Inference

MLCommons has released Endpoints v0.7, transforming inference testing from fixed-batch submissions into endpoint benchmarking infrastructure with automated review and continuous updates. The upcoming multi-turn agentic workloads will measure both per-user progress and aggregate throughput, rather than counting only tokens/s for isolated requests.

2026-08-02

形式驗證與 AI 求解

LeanCSP Verifies Constraint Rewriting and Solver Proofs in Lean, Reducing Search by Up to 20 Million Times

LeanCSP brings model equivalence, symmetry breaking, and solver-result checking into a single Lean 4 verification chain. External solvers still handle expensive searches, but invalid certificates cannot be turned into theorems by the Lean kernel.

2026-08-02

AI 安全

DFOT Quantifies LLM Over-Trust in Derived Sensor Values; Cross-Modal Distillation Improves Correction Rates by Up to 6.69 Points

A new framework breaks down “model over-trust in derived values” into metrics covering conflict acceptance, contextual misdirection, error correction, and utility harm. In a PPG-based rhythm interpretation case study, a reliability model that uses ECG during training but requires only PPG at deployment improves four endpoints, although the data and weights were not released with the code.

2026-08-01

DualG-MRAG Splits a Multimodal Knowledge Graph into Two Layers, Raising MMQA R@5 to 61.9%

DualG-MRAG uses a Macro Graph to find cross-document reasoning paths, then a Micro Graph to verify local image and text evidence, preventing fine-grained nodes from rapidly inflating the knowledge graph. In MMQA, the study raises R@5 from 42.1% for the strongest graph-based baseline to 61.9%, but the code and index construction costs have not yet been disclosed.

2026-08-01

代理工具

GRSD Assigns Rewards by Comparing an Agent’s Own Success and Failure Trajectories; ALFWorld Unseen Task Success Rate Reaches 83.6%

Group-Reflective Self-Distillation no longer extracts fixed skills from an external teacher. Instead, it compares successful and failed rollouts from the same policy and converts their differences into turn-level training signals. It delivers overall improvements across three agent environments, but increases training time by 17% over GRPO and still requires an external model to score reflection text.

2026-08-01

GitHub Repo

GCC Rejects Copyright-Significant LLM-Derived Content, While Maintainers May Make Exceptions for Generated Tests

The GCC Steering Committee has approved an AI contribution policy that generally rejects substantial code and text containing or derived from LLM output. Models may still be used for debugging, analysis, and review, and maintainers may accept generated tests, but their output cannot be incorporated directly into ordinary contributions.

2026-08-01

代理工具

Change2Task Ports Historical PRs to Modern Code, With 900 Agent Tasks Passing Three-Stage Validation

Change2Task extracts development intent from merged PRs, then reconstructs executable tasks on a modern version of the same repository. The study generated 900 task sets from 1,130 candidate changes, although most cases still required another coding agent to complete the reconstruction.

2026-08-01

代理工具

MemHarness Rewrites Agent Memory Before Acting, Raising 7B Model’s ALFWorld Success Rate to 85.2%

Instead of replaying retrieved past experiences verbatim, MemHarness has the same policy model critique and reorganize them based on the current state before deciding how to act. After end-to-end training with GRPO, it achieved success rates of 85.2% on ALFWorld and 75.6% on WebShop, though the code and model weights have not yet been released.

2026-08-01