Trajectory-Level Speculation with Semantic Verification for Tool-Using Agents
An analysis of SpecAgent, where a weaker model drafts tool calls and a stronger model verifies them, covering its design, experimental results, and limitations.
Benchmark Evaluation
4 pages
How Lossless Is Lossless Speculative Decoding? The Role of Numerical Precision in Orthrus
Is "Lossless" Speculative Decoding Really Lossless? — The Numerical-Precision Trap Exposed by Reproducing Orthrus TL;DR — Orthrus attaches a diffusion view to a frozen AR…
![[Paper Review] Qwen 3 Technical Report](https://qianwen-res.oss-accelerate-overseas.aliyuncs.com/logo_qwen3.png){kind=logo}
[Paper Review] Qwen 3 Technical Report
Qwen 3: The Evolution of a Giant MoE Language Model with Adjustable Reasoning Depth TL;DR (in one line) Qwen 3 couples a user-controllable Thinking Budget with a…
[Paper Review] Peri-LN: Revisiting Normalization Layer in the Transformer Architecture
Peri-LayerNorm: A Third Option Beyond Post-LN and Pre-LN TL;DR By simply adding another LayerNorm right after the residual connection—"Peri-LayerNorm (Peri-LN)"—the…