Leaderboards, eval harnesses and ablations — the contested business of deciding which model is actually better.
arXiv:2610.17256v1 Announce Type: new Abstract: Conversational analytics lets people ask questions of records spread across many systems and get answers in plain language; it is useful only if each a...
arXiv:2610.15373v1 Announce Type: cross Abstract: We adapted Nemotron-3-Nano-30B-A3B for eight Indian languages without changing its backbone architecture. We expanded the vocabulary in place from 13...
The paper introduces SCOPE, a framework that enables multiple scientist agents to pursue conjecture-driven research trajectories by modeling equations, formulating questions, and conducting active experiments, then sharing evidence to refine their conjectures. It also presents ClosureBench, an interactive benchmark of 60 closure-discovery tasks across five scientific domains, designed to evaluate equation discovery beyond accuracy by measuring evidence faithfulness, mechanism insight, and experimental effectiveness. Experiments show that SCOPE outperforms diverse baselines on both ClosureBench and a real-world scientific discovery case, yielding more accurate, reliable, and effective scientific discoveries.
arXiv:2410.12537v4 Announce Type: replace-cross Abstract: Complex query answering (CQA) on knowledge graphs (KGs) is gaining momentum as a challenging reasoning task. In this paper, we show that the...
arXiv:2610.19683v1 Announce Type: new Abstract: World models trained via latent dynamics offer a scalable path for embodied planning, yet existing methods suffer from representational collapse, compu...
arXiv:2610.19855v1 Announce Type: new Abstract: As Large Language Models (LLMs) continue to scale, their energy consumption during inference has become a critical concern. While Autoregressive (AR) m...
arXiv:2610.19878v1 Announce Type: new Abstract: Population dynamics are often observed only as unpaired snapshots, which leave the evolution between measurements underdetermined. Second-order regular...
The paper introduces Priming Models, a two‑stage framework for training one‑step generative models. First, the model is trained on a reconstruction objective such as pixel‑space denoising at a fixed noise level, then it undergoes feature‑space distributional post‑training. This simple reconstruction stage alone is shown to eliminate the difficulty of distributional training, leading to significant improvements in training compute versus generation quality across tasks like class‑conditional image generation, text‑to‑image generation, and world modeling, with a state‑of‑the‑art FID of 1.19 on ImageNet 256×256 using about one‑tenth the compute of previous methods.
arXiv:2508.03829v3 Announce Type: replace Abstract: The growing deployment of Large Language Models (LLMs) has raised concerns about their misuse in generating harmful or deceptive content. To addres...
arXiv:2504.17162v2 Announce Type: replace-cross Abstract: The subcellular localization of RNAs, including long non-coding RNAs (lncRNAs), messenger RNAs (mRNAs), microRNAs (miRNAs) and other smaller...
arXiv:2506.19549v2 Announce Type: replace-cross Abstract: Identifying which tokens and activations truly influence model predictions is critical for both the efficiency and interpretability of large...
arXiv:2610.20375v1 Announce Type: cross Abstract: Given $n$ distributions (hypotheses) $\mathcal H=\{H_1,\ldots,H_n\}$ and samples from an unknown target distribution $P$, proper hypothesis selection...
arXiv:2610.17718v1 Announce Type: new Abstract: Electrocardiogram (ECG) models need supervision that targets evolving weaknesses and remains faithful to waveform evidence. We introduce ECG-RSI, a rec...
arXiv:2610.18095v1 Announce Type: new Abstract: AI companions provide users with emotional support and ongoing companionship, but their sustained relational interactions also introduce distinct safet...
arXiv:2610.14542v1 Announce Type: new Abstract: Multimodal benchmarks are central to evaluating whether models can reason over information from multiple modalities. However, existing literature has r...
arXiv:2610.14539v1 Announce Type: new Abstract: Real-world business requests often leave key requirements unstated because frontline practitioners struggle to articulate rules they know from experien...
arXiv:2610.14700v1 Announce Type: new Abstract: Most text-to-SQL benchmarks provide the target database. In a large data catalog, however, choosing the sources is part of the problem: an agent must f...
arXiv:2610.14707v2 Announce Type: new Abstract: Expert-aligned "taste" benchmarks should reward craft judgment, not the ability to game the test. We introduce TasteBench, a pairwise good-vs-bad bench...
arXiv:2610.14918v1 Announce Type: new Abstract: Evaluating an agent's ability to strictly satisfy diverse and procedurally complex requirements is essential to determining its practical reliability....
arXiv:2610.14966v1 Announce Type: new Abstract: Long-horizon agents must complete workflows in which later activities depend on earlier outputs and changes to shared state. A key challenge for evalua...