…Sparse Mixture-of-Experts with Dense-Comparable Performance on End-Side Devices Published on May 11 Submitted by Chenyang Song on May 12 Tsinghua NLP Group Authors: , , , , , Abstract DECO is a sparse…
…Despite their strong performance on existing video benchmarks, we find that state-of-the-art MLLMs perform far below humans and only modestly above answer-prior baselines. To analyze this gap, we…
…Second, different one-shot expert compression methods converge to similar final performance after large-scale continual pretraining. Motivated by this, we introduce a simple partial-preservation expert merging strategy that improves downstream…
…Firstly, we review recent empirical practices and emerging methodologies that demonstrate the substantial performance gains achievable through deliberate language representation design, even without modifying model parameters or scale. Secondly, we conduct controlled…
…Taekhyun Park , , , Abstract LoopUS is a post-training framework that transforms pretrained LLMs into looped architectures for improved reasoning performance through latent-refinement and adaptive early exiting mechanisms. AI-generated summary Looped…
…The work also reveals that multimodal RLVR can improve performance even under blind training, suggesting that many gains may come from residual textual cues rather than genuine visual reasoning. Get this paper…
Papers arxiv:2604.26326 Addressing Performance Saturation for LLM RL via Precise Entropy Curve Control Published on May 10 Submitted by Bolian Li on May 12 Purdue University Authors: Bolian Li , Yifan…
…AI-generated summary This paper proposes a novel approach to address the challenge that pretrained VLA models often fail to effectively improve performance and reduce adaptation costs during standard supervised finetuning (SFT…
…Yihong Liu , , , Abstract COPSD transfers high-resource language model reasoning behavior to low-resource languages using self-distillation with crosslingual context, improving mathematical reasoning performance. AI-generated summary Large language models (LLMs…
…We also find that providing access to client profiles yields an average performance gain of 18.24\%, highlighting the importance of user-specific information for effective persuasion . Overall, our work highlights persona…