Leaderboards, eval harnesses and ablations — the contested business of deciding which model is actually better.
arXiv:2609.24095v1 Announce Type: new Abstract: While deep learning has enabled language decoding from intracranial brain recordings, extending this capability to non-invasive recordings remains an u...
arXiv:2609.23457v1 Announce Type: new Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) is expanding from tasks with well-defined correctness signals, such as mathematics and code, towa...
arXiv:2601.15322v3 Announce Type: replace-cross Abstract: Tool-using agents can repeat a final decision while changing their recorded execution. We introduce the Determinism-Faithfulness Assurance Ha...
arXiv:2609.24443v1 Announce Type: cross Abstract: Reliable disruption prediction is essential for the safe operation of future tokamaks. Existing full-distribution survival methods model the complete...
arXiv:2609.23038v1 Announce Type: cross Abstract: Spatial reasoning is essential for vision-language models (VLMs) to understand and act in the physical world. Reasoning in dynamic environments requi...
arXiv:2609.23465v1 Announce Type: new Abstract: Long-horizon conversational memory is especially challenging in multi-actor settings, where relevant evidence is distributed across participants and co...
arXiv:2609.25001v1 Announce Type: new Abstract: Modern video games provide a measurable testbed for AI models, combining abilities of visual understanding, instruction decomposition, goal planning, a...
arXiv:2511.04473v3 Announce Type: replace Abstract: Retrieval of information from graph-structured knowledge bases represents a promising direction for improving the factuality of LLMs. While various...
arXiv:2609.22917v1 Announce Type: new Abstract: Non-technical stakeholders frequently cannot write the SQL needed to extract insights from operational databases. We built and evaluated a Text-to-SQL...
arXiv:2609.23961v1 Announce Type: new Abstract: Monocular colonoscopic 3D reconstruction is important for surgical robotic colonoscopy, but remains challenging due to weak texture, specular reflectio...
The paper introduces BAS‑VLA, a task‑semantic action calibration framework for vision‑language‑action models that addresses two failure modes: unnecessary action drift under appearance changes and insufficient behavioral change under semantic alterations. BAS‑VLA uses a breaking‑centered calibration core and a selective evidence‑gated preserving auxiliary to maintain performance on clean and semantics‑preserving conditions while suppressing stale‑task behavior. Experiments on OpenPI‑pi0.5 and LIBERO‑Object Milk‑Swap show high success rates on clean and preserved tasks, a dramatic drop under target‑object swaps, and improved robustness to style shifts from 42% to 70% without harming clean performance.
arXiv:2605.29310v2 Announce Type: replace-cross Abstract: Stepwise model routing improves the efficiency of Large Reasoning Models (LRMs) by assigning each reasoning step to a suitable model. Recent...
Predicting early outcomes based on trajectory can decrease the expenses associated with agent evaluation by terminating a run once the outcome becomes sufficiently predictable, assuming that the predi...
Exhaustively evaluating every candidate LLM configuration on every benchmark item to identify a high-performing one is costly. We formulate configuration selection as a cost-aware Bayesian bandit prob...
Soccer tactics are interactive: an attacking action changes the opponent's defensive problem, and the observed response depends on the multi-agent match state. We introduce SambaGraph, an action--reac...
Standard deployment-ready object detectors for autonomous vehicles degrade in adverse weather and lighting conditions without being trained on extensive domain-specific data. While large-scale vision...
TypeSafe AI’s new model, Jev, is a ‘System One’ or decision model that takes text or semi‑structured data as input and outputs floating‑point probabilities for yes/no, choice, or score questions, rather than text. It charges only for input tokens ($0.042/million) and offers free output, making it cheaper and faster than typical LLMs. The API lets users build a state object (string, array, or key‑value pairs) and query it with multiple questions, receiving confidence scores and probability distributions for each answer.
Legal argument mining supports passage classification, retrieval, and argument completion. This work introduces an expert-annotated dataset of 42 U.S. federal tax opinions on corporate reorganizations...
Post-training is becoming a service (PTaaS): a customer hands an operator data and a goal, and a forward-deployed engineer (FDE) returns a fine-tuned, evaluated, and deployed model under a budget, a h...