Leaderboards, eval harnesses and ablations — the contested business of deciding which model is actually better.
arXiv:2603. 05353v2 Announce Type: replace Abstract: Retrieval-augmented generation (RAG) for long-context question answering is bottlenecked by inference-time prefilling over large retrieved contexts.
arXiv:2606. 30966v1 Announce Type: new Abstract: Formal specification is a powerful tool to guide the learning process and provides significant advantages over reward shaping: (1) mathematical rigor; (2) expressiveness to specify objectives and constraints, and (3) the ability to define tactics to achieve objectives.
arXiv:2606. 30695v1 Announce Type: cross Abstract: Single-cell drug perturbation models should predict not only transcriptional response magnitude, but also whether a treatment alters the proliferative state of a cell.
arXiv:2606. 31672v1 Announce Type: cross Abstract: Despite rapid progress in interactive world models (IWMs), existing benchmarks evaluate action following only at trajectory level and ignore memory and interaction physics.
arXiv:2604. 09731v2 Announce Type: replace-cross Abstract: Tree-based speculative decoding accelerates autoregressive generation by verifying a branching tree of draft tokens in a single target-model forward pass.
arXiv:2606. 30842v1 Announce Type: new Abstract: Outbreak transmission reconstruction treats epidemiological timing and transmission labels as deterministic ground truth; neither has been systematically evaluated.
arXiv:2606. 31966v1 Announce Type: cross Abstract: Recent multimodal large language models (MLLMs) have strong potential as embodied agents, but their ability to collaborate in visually grounded environments remains underexplored.
arXiv:2512. 04390v2 Announce Type: replace-cross Abstract: Joint video super-resolution and deblurring (VSRDB) requires both efficient long-range temporal modeling and robustness to frame-wise exposure-duration variation, which changes the extent of motion blur across video frames.
arXiv:2606. 32034v1 Announce Type: cross Abstract: LLM agents increasingly act over long horizons, where a single trajectory can contain hundreds or thousands of actions.
arXiv:2604. 17931v3 Announce Type: replace Abstract: Reinforcement Learning (RL) has emerged as a powerful training paradigm for LLM-based agents.
arXiv:2603. 23297v2 Announce Type: replace-cross Abstract: Despite their output being ultimately consumed by human viewers, 3D Gaussian Splatting (3DGS) methods often rely on ad-hoc combinations of pixel-level losses, resulting in blurry renderings.
arXiv:2603. 19127v2 Announce Type: replace Abstract: As Spoken Language Models (SLMs) integrate speech and text modalities, they inherit the safety vulnerabilities of their LLM backbone while introducing an expanded attack surface.
arXiv:2606. 31332v1 Announce Type: new Abstract: Protein automodeling from cryo-EM density maps faces unique challenges in enforcing physicochemical validity and managing conformational heterogeneity.
arXiv:2606. 30995v1 Announce Type: new Abstract: Recent work has shown that well-optimized individual decision trees can match complex black box models in some settings, primarily in noisy domains.
arXiv:2606. 31577v1 Announce Type: cross Abstract: Conformal predictions have attracted significant attention in the field of uncertainty quantification, mainly because of their strong marginal coverage guarantees.
arXiv:2603. 16250v2 Announce Type: replace-cross Abstract: LVLMs encounter significant challenges in image understanding and visual reasoning, leading to critical perception failures.
arXiv:2606. 31179v1 Announce Type: new Abstract: As AI agents become increasingly capable of complex, long-horizon reasoning, rigorous and holistic evaluation is essential for measuring progress toward real-world healthcare applications.
arXiv:2606. 30961v1 Announce Type: cross Abstract: Advances in deep learning architectures and representations have enabled ML-driven chemical property prediction, but state-of-the-art (SOTA) models have remained largely confined to independent codebases and lack support for diverse chemical species.
arXiv:2606. 30911v1 Announce Type: new Abstract: ML engineering agents waste compute rediscovering known techniques because every competition is a cold start.
arXiv:2606. 32007v1 Announce Type: new Abstract: We study agentic code generation in Dafny, where a model must generate both executable code and the proof artifacts for verification.