Leaderboards, eval harnesses and ablations — the contested business of deciding which model is actually better.
Evaluating deformable 3D reconstruction requires ground truth linking camera motion, surface deformation, material correspondence and image appearance. We introduce the Synthetic Deformable Tubular Be...
Structure-from-motion (SfM) from the dual-fisheye video of a consumer 360-degree camera recovers geometry only up to a similarity transform; in the pipeline considered here, metric scale is obtained f...
Large organizations consume large language models (LLMs) from several vendors at once, each with its own API dialect, credential model, streaming protocol and pricing. Integrated directly, this hetero...
Many decision-making tasks are inherently multi-objective. Interactive evolutionary multi-objective optimization algorithms (iEMOAs) are particularly well-suited to help the decision-maker find their...
Referring expression grounding in overhead imagery requires oriented bounding boxes rather than horizontal ones, since aerial objects appear at arbitrary orientations. Most grounding models emit box c...
Structured sparse learning is a leading paradigm for high-dimensional data modeling, as it enables rigorous integration of domain-validated structural priors into the learning process. Among these pri...
We address a fundamental question: How far should kernel fusion extend and which boundaries are worth preserving? Unlike the general convention of using one monolith megakernel at lower batch sizes or...
We present GaussianSpline, a dynamic 4D Gaussian Splatting method that models per-Gaussian motion using adaptive, non-uniform piecewise cubic Bézier splines. Unlike approaches based on global deformat...
The article compares Claude Code and Cursor by presenting a field test that reveals differing token usage: one benchmark shows Claude Code using 33,000 tokens versus Cursor’s 188,000, while another benchmark shows the opposite. The post aims to provide a definitive comparison for teams deciding between the two tools.
Understanding and operating with scientific charts is a standard approach in data analysis, and while humans are good at interpreting such charts, open vision-language models (VLMs) are known to perfo...
Simultaneous speech translation (SimulST) aims to translate ongoing speech with low latency while preserving translation quality. Recent studies have adopted large language models (LLMs) for SimulST a...
Text-steerable visual encoders condition a frozen Vision Transformer on a natural-language prompt and point at the matching image region, producing prompt-conditioned heatmaps and features. We audit t...
Modern large language models (LLMs) often exhibit overconfident errors, assigning high confidence to incorrect predictions and thereby undermining reliability in real-world use. Existing calibration m...
Background: Understanding individual predictions in complex tabular models remains challenging, as existing additive frameworks like SHAP and LIME often obscure structural logic by absorbing nonlinear...
Despite the remarkable capabilities of large language models (LLMs) across diverse applications, they remain vulnerable to generating content that violates safety regulations and policies. To mitigate...
Grasping is a foundational capability in robotic manipulation. Scene-level 6-DoF grasp synthesis relies on point clouds for metric geometry, yet real-world point observations are often noisy, incomple...
Point cloud models are increasingly deployed through score-only black-box interfaces. Under this access model, test-time rotations outside the training distribution can substantially degrade performan...
Retrieval-augmented generation (RAG) systems often use a dedicated reranker to choose which retrieved candidates reach the language model. Reranking improves relevance but adds latency, so teams look...
HarnessMM (Harness Minus Minus) is a method that improves harness token efficiency by using guarded decision reuse and recursive self‑improvement (RSI). It refines harness configurations from training feedback, reuses resolved decisions to replace later reasoning callbacks, and stores actions in Executable Decision Graphs. Experiments show significant token savings while maintaining or improving success rates on benchmarks such as HumanEval and DeepSeek Harness.
The paper investigates how large language models (LLMs) can be distributionally aligned with human output distributions, particularly for applications like survey simulation. It examines both the alignment process and the models’ ability to generalize to unseen questions within the same domain and to related but different topics. The study finds that while LLMs can achieve alignment and generalize within a domain, cross‑topic generalization is variable and aligned models may unexpectedly lose creative capabilities, indicating unpredictable and unstable generalization properties.