…Length-Efficient Adaptive and Dynamic Reasoning for LLMs! Reasoning LLMs are great at solving hard problems, but they tend to "think longer to think better" — even when the problem doesn't need…
…AI-generated summary Agentic modeling aims to transform LLMs into autonomous agents capable of solving complex tasks through planning , reasoning , tool use , and multi-turn interaction with environments. Despite major investment, open…
…a self-improvement phase, where the model uses RL to generate a curriculum of synthetic data to rehearse new knowledge and refine existing capabilities without human supervision. Our experiments on long-horizon…
…To better understand the political rhetoric from various movements, ranging from left to right, we propose a transformer-based model capable of projecting the political orientation of a text on a continuous…
…A Multitask Benchmark and Model for Code Search Published on May 6 Submitted by Ziyin Zhang on May 11 high-quality llm benchmarks Authors: , , , Ziyin Zhang , , , Hang Yu Abstract A new code…
…gating weights obtained from narrow-domain fine-tuning substantially suppress broad-domain misaligned behavior while preserving the model's general capabilities. View arXiv page View PDF GitHub 5 Add to collection Community…
…Jiahao Wang , An Ping , , , , , , , Han Wang , , , , , , , Abstract OmniCap-IF is introduced as the first comprehensive benchmark for evaluating instruction-following capabilities in omni-modal captioning, revealing significant performance disparities and a format…
…To address this problem, we propose a new benchmark CUActSpot for evaluating models' capabilities on complex interactions across five modalities: GUI, text, table, canvas, and natural image, as well as a variety…
…We then train a family of capable Claw-style models, termed ClawGym-Agents , through supervised fine-tuning on black-box rollout trajectories , and further explore reinforcement learning via a lightweight pipeline that…
…AI-generated summary In this paper, we propose AlphaGRPO, a novel framework that applies Group Relative Policy Optimization (GRPO) to AR-Diffusion Unified Multimodal Models (UMMs) to enhance multimodal generation capabilities without…