…horizon optimization . In parallel, RubricEM trains a shared-backbone reflection meta-policy that distills judged trajectories into reusable rubric-grounded guidance for future attempts. The resulting RubricEM-8B achieves strong performance across…
…Dan Jacobellis , Abstract LiVeAction is a lightweight neural codec architecture that improves rate-distortion performance for resource-constrained devices by using an FFT-like structure and variance-based rate penalty instead of…
…Across three fundamentally distinct benchmarks including LoCoMo, Mind2Web, and GAIA, FluxMem achieves consistent state-of-the-art performance, demonstrating strong adaptation and generalization in complex agentic environments. The code will be open…
…Yet recurrent architectures remain unstable to train, costly to optimize and deploy, and constrained to small, fixed recurrence depths. We introduce Attractor Models , in which a backbone module first proposes output embeddings…
…Yangyi Huang , , , , , , Weiyang Liu Abstract Parameter-efficient fine-tuning methods exhibit varying stability-plasticity trade-offs in preserving pretrained capabilities, with orthogonal fine-tuning showing optimal performance under similar parameter constraints. AI…
…Jingjie Ning , , , , Abstract Auto research operates as an empirical loop where agents iteratively refine code based on evaluation feedback, achieving improved performance across multiple tasks without human intervention. AI-generated summary We…
…the reward sparsity induced by scalar-valued rewards, and the gradient interference arising from jointly optimizing heterogeneous objectives, which together give rise to a 'seesaw effect' of competing metrics and pervasive reward…
…1% in average accuracy) despite adequate static retrieval performance. Prompt optimization, deeper retrieval, reduced filler noise, and most stronger LLMs fail to close this gap. Only a file-based agent paired with…
…The same trained reverse process performs generation and continuous super-resolution by varying only the starting timestep: no task-specific architecture, no conditioning branch, no classifier-free guidance, no retraining per scale…
…I was able to perform a rough comparison between Dots.OCR.Runner and other VLMs such as Magistral-Small-2509 and qwen3-vl-30b , using their top quantized versions that can run…