…A novel approach decouples auxiliary training objectives from standard supervised finetuning to enhance model capabilities while reducing computational overhead through capability vector merging and orthogonal regularization. AI-generated summary This paper proposes…
…With only 0.02% of internet content in African languages and Africa contributing less than 1% to global AI training data, initiatives like UCCB are essential for building more inclusive AI systems…
…in tabular foundation models by sequentially applying data cleaning operators to align real-world data with synthetic training distributions, improving both accuracy and calibration. AI-generated summary Tabular Foundation Models (TFMs) achieve…
…scale human-centric video dataset with rich annotations for embodied intelligence, demonstrating that egocentric human video can effectively replace robot data for training vision-language-action models. AI-generated summary Progress in…
…embodied AI training. However, scaling to long interactive trajectories is prohibitively expensive due to growing context memory, quadratic attention complexity, and repeated denoising steps. We present Light Interaction, a training-free inference…
…framework enables autonomous large language model self-improvement through co-evolutionary training with intrinsic rewards and hint-based guidance. AI-generated summary Self-evolving LLMs excel in verifiable domains but struggle in…
…Ming Li , , , , , Abstract Scaling visual preference optimization requires addressing noisy datasets through adaptive Poly-DPO methodology and high-quality data construction, achieving superior performance over existing approaches. AI-generated summary While preference…
…AI-generated summary We introduce Pion, a spectrum-preserving optimizer for large language model (LLM) training based on orthogonal equivalence transformation . Unlike additive optimizers such as Adam and Muon , Pion updates each…
…AI-generated summary Reinforcement learning (RL) has been applied to improve large language model (LLM) reasoning, yet the systematic study of how training scales with task difficulty has been hampered by the…
…AI-generated summary Recent generative models can produce images that appear highly realistic, raising challenges in distinguishing real and AI-generated images. Yet existing detectors based on pre-trained feature extractors tend…
