…highly amenable to diffusion modeling. To optimize computational efficiency, we leverage an asymmetric and attention-free encoder-decoder backbone to minimize encoding overhead. We present a comprehensive evaluation of Qwen-Image-VAE…
…The generation pipeline leverages a vision-language model (VLM) to design and compose subtasks, generates full trajectories through atomic functions , and provides memory-related annotations , including subtask instructions and native keyframe annotations…
…Benchmarking Multimodal Long-Term Memory in Large Vision-Language Models Published on May 14 Submitted by Zhaowei Wang on May 15 NVIDIA Authors: Xiyu Ren , , Yiming Du , , , , , , , , , , , Abstract A new benchmark evaluates…
…Submitted by Shivam Kumar on May 14 Authors: Shivam Kumar Abstract ShapeCodeBench presents a synthetic benchmark for perception-to-program reconstruction where models generate executable drawing programs from raster images, evaluated on…
…A Comprehensive Benchmark for Evaluating LLM-Generated GPU Kernels Published on May 6 Submitted by Jintao Zhang on May 8 Tsinghua University Authors: , Jintao Zhang , , , , Abstract KernelBench-X benchmark reveals that task…
…Sleeper Attack on Large Language Model Agents (2026) AgentCanary: A Security Evaluation Framework for Autonomous AI Agents in Real Executable Environments (2026) Benchmarking Autonomous Agents against Temporal, Spatial, and Semantic Evasions (2026…
…Evaluating Long-Term Agent Memory Toward Experienced Colleagues Published on May 12 Submitted by Di Wu on May 13 UCLA NLP Authors: , , , , , , Abstract A new benchmark called LongMemEval-V2 is introduced to…
…However, scalable development around these environments remains constrained by the absence of a systematic framework, especially one for synthesizing verifiable training data and integrating it with agent training and diagnostic evaluation . To…
…Evaluating 7 models from 4 families, safety improves by 9--52% as the number of preceding regular agentic tasks increases from zero to twenty. Representation analysis confirms that model hidden states gradually…
…designing the prompts, tools, orchestration logic, and evaluation criteria that make a foundation model effective. We present a two-level framework that automates this process. At the first level, the Harness Evolution…