Leaderboards, eval harnesses and ablations — the contested business of deciding which model is actually better.
arXiv:2605. 00527v3 Announce Type: replace-cross Abstract: Lissajous confocal laser endomicroscopy (CLE) is a promising solution for high-speed in vivo optical biopsy for handheld scenarios.
arXiv:2606. 22357v2 Announce Type: replace-cross Abstract: Language models are widely used in assistant settings, where controlling behavioral attributes is often essential.
arXiv:2604. 03919v2 Announce Type: replace-cross Abstract: We present the first systematic study of Sparse Autoencoders (SAEs) on video representations.
arXiv:2605. 12530v2 Announce Type: replace-cross Abstract: LLM fairness should be evaluated through in-situ behavioral pattern rather than standardized-test Q&A benchmarks.
arXiv:2608. 08317v1 Announce Type: new Abstract: Biological neural systems achieve high efficiency and robustness through compartmentalized architectures.
arXiv:2608. 08440v1 Announce Type: new Abstract: Cross-subject electroencephalogram (EEG)-based emotion recognition remains challenging due to substantial inter-individual variability and discrete formulation that overlooks affective continuity.
arXiv:2608. 08964v1 Announce Type: new Abstract: The generation of mathematically precise diagrams from tex- tual prompts has emerged as a critical yet underexplored capability of Large Language Models (LLMs).
arXiv:2608. 08652v1 Announce Type: cross Abstract: We present \LegoLM{}, a structured weight-sharing compression framework for large language models grounded in a systematic study of why global weight sharing fails and how to fix it.
arXiv:2608. 08722v1 Announce Type: cross Abstract: Benchmarks for systems that are optimized against the evaluation signal measure something different from what they claim.
arXiv:2608. 09768v1 Announce Type: new Abstract: A prediction that is both confident and wrong is a critical reliability failure because it can bypass abstention and human review precisely when the model is mistaken.
arXiv:2608. 09251v1 Announce Type: cross Abstract: Large language model-based multi-agent systems have recently shown strong potential for complex, long-horizon tasks.
arXiv:2608. 09260v1 Announce Type: cross Abstract: Large language models (LLMs) have advanced Text-to-SQL by enabling natural language interfaces to databases without task-specific fine-tuning.
arXiv:2608. 09564v1 Announce Type: cross Abstract: UAV vision-language navigation (UAV-VLN) focuses on enabling an aerial agent to follow natural-language instructions in open 3D environments from egocentric visual observations.
arXiv:2608. 09636v1 Announce Type: cross Abstract: Accurate 3D neuron segmentation in fluorescence microscopy is critical for neuroscience.
arXiv:2608. 09745v1 Announce Type: cross Abstract: On-policy self-distillation (OPSD) converts feedback into dense token-level supervision on trajectories generated by the policy to be optimized, providing a useful complement to reinforcement learning with sparse outcome rewards.
arXiv:2608. 09930v1 Announce Type: cross Abstract: Automated Text-to-Speech (TTS) evaluation methods (Mean Opinion Score (MOS) predictors and Audio Large Language Models (Audio-LLM) judges) are expected to reflect human perception, yet it is unclear how well they capture the distinct aspects of speech that listeners actually perceive.
arXiv:2512. 10282v4 Announce Type: replace Abstract: Attention improves representation learning over RNNs, but its discrete nature limits continuous-time (CT) modeling.
arXiv:2601. 09974v2 Announce Type: replace Abstract: Personalizing Large Language Models typically relies on static retrieval or one-time adaptation, assuming user preferences remain invariant over time.
arXiv:2505. 11146v3 Announce Type: replace-cross Abstract: Fine-grained facial expression transfer from humans to humanoid agents presents a unique pattern recognition challenge due to the significant domain gap between biological facial dynamics and mechanical control spaces.
arXiv:2308. 04553v4 Announce Type: replace-cross Abstract: Visual recognition models are prone to learning spurious correlations induced by a biased training set where certain conditions $B$ (\eg, Indoors) are over-represented in certain classes $Y$ (\eg, Big Dogs).