JET: Justification Evaluation in Transformer

vla.simd: Efficient CPU Inference for Language-Conditioned Manipulation

This work presents vla.simd, a CPU inference engine that combines shared SIMD micro-kernels, reusable computation, and target-specific optimization, and introduces IMPACT, an ACT-based policy with cached text representations and language-modulated visual features.

SCX Router: Streaming Zero-Shot Model Selection with a Decoder-KV Classifier and a Real-World Task Ontology

A lightweight GLiClass-based router is introduced, a lightweight GLiClass-based router that assigns a suitability score to each inference-time model label without autoregressive generation, and a released 0.6B-parameter checkpoint combines a Qwen3 decoder with a shallow bidirectional scorer.

How Much Can Language Models Gain from Test-Time Computation?

How much can test-time computation improve a language model, and at what cost? Test-time scaling is widely proposed as a substitute for larger models, but existing comparisons mostly evaluate one domain at a time and rarely charge selection to the budget. We introduce SELF-POT, a benchmark and evaluation framework that...

Investigating the Impact of Supervision Format on Reasoning Performance in Large Language Models

Treating supervision format as a first-class hyperparameter for multi-task reasoning SFT in large language models—at least in this benchmark-and-model setting—rather than a mere rendering detail is supported.

Optimizing Inference Stability in Small Language Models using Invariant Pruning and Audited Synthesis

Task-Aware Spectral Pruning: A Mixture-of-Masks Framework for Efficient LLM Inference

Task-Aware Spectral Pruning (TASP), a post-training framework that calibrates module-level spectral descriptors against measured task-specific ablation effects, closes grouped-query-attention and SwiGLU dependencies during sparse-mask construction, and routes each user turn to one compiled mask that remains fixed throu...