Leaderboards, eval harnesses and ablations — the contested business of deciding which model is actually better.
arXiv:2601.19747v2 Announce Type: replace-cross Abstract: In the rapidly evolving field of Electronic Design Automation (EDA), the deployment of Large Language Models (LLMs) for Register-Transfer Lev...
arXiv:2605.29001v2 Announce Type: replace-cross Abstract: A paraphrase-quality audit of MathCheck (ICLR 2025) detected 4 semantically incorrect paraphrases in 129 groups (3.1%); removing them drops G...
arXiv:2610.22661v1 Announce Type: new Abstract: Human-AI interactions are becoming a rich source of data for improving AI systems: while many model responses are already satisfactory, others expose f...
arXiv:2610.15829v2 Announce Type: replace Abstract: Hard-margin SVM training is the distance problem between two convex hulls, which the Triangle Algorithm (TA) solves with a certified duality gap. W...
arXiv:2509.01253v2 Announce Type: replace-cross Abstract: In contemporary cloud-based services, protecting users' sensitive data and ensuring the confidentiality of the server's model are critical. F...
arXiv:2601.00581v3 Announce Type: replace-cross Abstract: We introduce AceFF, a pre-trained machine learning interatomic potential (MLIP) optimized for small molecule drug discovery. While MLIPs have...
arXiv:2610.22980v1 Announce Type: new Abstract: Large language model (LLM) agents are increasingly evaluated on long-horizon tasks, including autonomously running a business. Existing benchmarks for...
arXiv:2610.23062v1 Announce Type: new Abstract: Multi-objective optimization models are often deployed in settings where decision makers (DMs) must balance some conflicting criteria. In practice, how...
arXiv:2610.23254v1 Announce Type: new Abstract: Tool-using agents read untrusted external content, which exposes them to indirect prompt injection (IPI), where hidden instructions hijack the agent's...
arXiv:2610.23521v1 Announce Type: new Abstract: Large language models (LLMs) can now perceive, describe, and reason about images and audio, yet time series understanding remains underestimated: most...
In time-series forecasting tasks, the use of recursive forecasting on high-dimensional data substantially increases the complexity of the prediction process. The main challenge is that long-term dynam...
The article reports that the author reran Python 3.14 JIT benchmarks on Python 3.15, observing a significantly stronger Just-In-Time (JIT) performance across the same three workloads. However, the improved JIT does not universally benefit all programs, indicating that performance gains are workload‑dependent.
The paper introduces Temporal Specification Guidance (TSG), a training‑free inference framework that uses Temporal Logic specifications to guide text‑to‑video generation. TSG evaluates visual concept traces with differentiable quantitative semantics and adjusts the denoising direction via gradient‑derived attention biases, eliminating the need for external classifiers or backpropagation through the transformer. Experiments on 220 prompts across 11 temporal constraint categories show that TSG improves specification satisfaction by 9.5–20 percentage points over classifier‑free guidance with minimal memory overhead.
OmicsBench is a new long‑horizon, multi‑turn bioinformatics benchmark for AI agents, comprising 97 tasks that link 662 subtasks into directed acyclic graphs. Each subtask is a user turn scored deterministically, with optional in‑context feedback. Across 12 models, agents achieve mean scores between 0.43 and 0.67, revealing lower performance on dependent subtasks and highlighting qualitative failure modes through an unsupervised discovery pipeline.
The paper presents numerical evidence that topological freezing in SU(3) Yang‑Mills theory can be reduced using a flow‑based method. By combining open boundary conditions with Stochastic Normalizing Flows, the authors analyze how computational costs scale at lattice spacings as fine as 0.03 fm. They find that both the integrated autocorrelation time of the squared topological charge and the statistical uncertainty on the topological susceptibility stay under control across the explored parameter range with current computational resources.
The paper introduces PhysClosureBench, a benchmark of 50 expert‑verified physics research tasks that test whether AI agents can organize investigations and produce evidence‑supported conclusions. Each task specifies a research goal and constraints, while the agent must design the investigation and validate evidence. Seven leading LLMs were evaluated, with Claude‑Opus‑5 scoring highest on local scientific accomplishment but achieving full research closure (RC4) only 32.7% of the time, revealing a gap between local success and complete closure.
The paper introduces GUISE, a benchmark of criminal‑assistance scenarios drawn from real‑world cases and organized using the UNODC International Classification of Crime for Statistical Purposes. It evaluates large language models under three linguistic framings and across five cultures, finding that framing and cultural adaptation significantly increase unsafe compliance rates. The study also shows that unsafe responses from the least‑safe models exhibit strong Anglocentric language, with leakage growing alongside harmfulness.
PocketTSLM is a mobile-native deployment of the OpenTSLM SoftPrompt time‑series language model that runs entirely on a consumer smartphone. By injecting encoded time‑series windows as embeddings instead of tokenizing them as text, PocketTSLM preserves temporal structure while using far fewer tokens and staying within the device’s context and memory limits. The model has been benchmarked on 30‑second EEG sleep‑staging clips and 10‑second ECG recordings, achieving on‑device inference with no health data transmitted to the cloud.
The paper introduces Align Latent Rollout (ALR), a regularization technique for neural PDE solvers that encourages consistency across different rollout origins. ALR uses a second‑order Taylor analysis to define two objectives: zeroth‑order consistency aligning latent states at a shared target time, and first‑order consistency aligning local evolution responses to perturbations. The method can be applied to various neural PDE solvers without altering their architectures and demonstrates improved prediction accuracy and reduced discrepancies across rollout origins in multiple benchmarks.
The paper introduces training‑free on‑policy distillation, a method that consolidates multiple specialist models into a single student without any gradient updates. By performing only forward passes over a few hundred rollouts, the fused model can reproduce each specialist’s outputs layer‑by‑layer, achieving higher average accuracy than any individual specialist. The approach relies on a least‑squares solution that uses only the second moments of inputs, and careful handling of rollouts—such as removing repetitive answers—significantly improves performance on benchmarks like AIME25 and Olmo 3‑7B.