Leaderboards, eval harnesses and ablations — the contested business of deciding which model is actually better.
arXiv:2607. 16206v1 Announce Type: new Abstract: This paper introduces PPO-HSC (Proximal Policy Optimization with High-order Sampling Coverage), an exploratory reinforcement learning framework designed to address the "Invisible Shackles" of mode collapse in Large Language Model (LLM) fine-tuning.
arXiv:2607. 17108v1 Announce Type: new Abstract: In multi-hop RAG evaluation, a top-k answer score can hide two different failures: the retrieval window may drop part of the support chain, or it may contain support in a form the adapted reader does not use well.
arXiv:2607. 17610v1 Announce Type: cross Abstract: Automatic image colorization enables large-scale and low-cost reuse of grayscale media (e.
arXiv:2603. 07598v2 Announce Type: replace Abstract: Chain-of-thought (CoT) reasoning improves problem solving, but long think traces increase inference cost.
arXiv:2605. 30664v2 Announce Type: replace Abstract: Subgoal-based policy tree search, which uses a policy to guide search, is effective for complex single-agent deterministic problems but often relies on explicit subgoal generation that can incur substantial overhead and hinders scalability.
arXiv:2607. 18199v1 Announce Type: cross Abstract: Not all training samples contribute equally to large language model fine-tuning.
arXiv:2607. 16685v1 Announce Type: cross Abstract: Conditional diffusion models have become a powerful and flexible framework for learning complex conditional distributions from labeled data.
arXiv:2607. 16736v1 Announce Type: cross Abstract: This paper presents RealDESED, a real-world domestic sound event detection (SED) benchmark comprising 5,710 audio recordings collected by 652 participants in their homes.
arXiv:2607. 17842v1 Announce Type: cross Abstract: Recent breakthroughs in 3D Gaussian Splatting (3DGS) have advanced neural rendering with high fidelity and speed.
arXiv:2602. 05463v2 Announce Type: replace-cross Abstract: Modern AI systems achieve remarkable capabilities at the cost of substantial energy consumption.
arXiv:2603. 13065v2 Announce Type: replace-cross Abstract: Deep learning models achieve high accuracy in time series classification, yet understanding their class-level decision behaviour remains challenging.
arXiv:2603. 29219v2 Announce Type: replace-cross Abstract: Sign language is the primary approach of communication for the Deaf and Hard-of-Hearing (DHH) community.
arXiv:2510. 27497v2 Announce Type: replace-cross Abstract: Transformer-based autoregressive models have emerged as a unifying paradigm across modalities such as text and images, but their extension to 3D molecule generation remains underexplored.
arXiv:2503. 08245v4 Announce Type: replace Abstract: In mixed graphs, there are both directed and bidirected edges.
arXiv:2607. 17762v1 Announce Type: cross Abstract: Large language model (LLM)-driven evolutionary search is an emerging algorithm-discovery paradigm that has already produced novel results in several scientific fields.
arXiv:2607. 18130v1 Announce Type: new Abstract: Most parameter-efficient finetuning (PEFT) methods adapt weights or activations, thus leaving one of the key Transformer components unchanged: residual connections.
arXiv:2607. 16682v1 Announce Type: cross Abstract: The widespread adoption of high-level deep learning libraries, while accelerating model development, has increasingly abstracted away the internal mechanics of neural networks, creating a gap between practical usage and fundamental understanding.
arXiv:2607. 16286v1 Announce Type: cross Abstract: The 3D geometry of real-world scene data is often incomplete.
arXiv:2607. 16242v1 Announce Type: cross Abstract: Fine-Tuning-as-a-Service (FTaaS) platforms let users train large language models (LLMs) on customized tasks, but this pipeline could erode models' safety alignment.
arXiv:2607. 16240v1 Announce Type: cross Abstract: Direct Alignment Algorithms (DAAs) such as DPO have become a common way to post-train and align LLMs with human preferences.