KVzap: Fast, Adaptive, and Faithful KV Cache Pruning

NVIDIA has announced the rollout of DLSS 4.5, a significant update for all RTX GPUs, enhancing gaming performance and visual fidelity. This update is expected to improve frame rates and overall gaming experiences for users of NVIDIA's graphics cards.

A new technical paradigm called ExpSeek has been introduced, enhancing web agents' interaction capabilities by enabling proactive experience seeking rather than passive experience injection. This approach utilizes step-level entropy thresholds to optimize intervention timing and tailor-designed experience content, demonstrating significant performance improvements in Qwen3-8B and Qwen3-32B models across various benchmarks.

Recent advancements in multilingual reasoning models have been highlighted with the introduction of Language-Mixed Chain-of-Thought (CoT), which utilizes English as an anchor to enhance reasoning in other languages, specifically Korean. The study presents the KO-REAson-35B model, which achieved state-of-the-art performance in reasoning tasks, supported by a curated dataset of Korean prompts known as Yi-Sang.

ToolRM has been introduced as a new family of lightweight reward models specifically designed for tool-use scenarios, addressing the limitations of existing reward models in aligning large language models (LLMs) with human preferences. This development includes a novel pipeline for generating high-quality preference data and a benchmark for evaluating these models on tool-calling tasks.