Leaderboards, eval harnesses and ablations — the contested business of deciding which model is actually better.
arXiv:2610.22744v1 Announce Type: new Abstract: Creative intent in video editing can be expressed through text instructions (e.g., "remove the people"), image references (e.g., subject appearance), v...
arXiv:2610.22751v1 Announce Type: new Abstract: Medical vision-language models (VLMs) for visual question answering (VQA) often pass long visual-token sequences to the language model, making visual-t...
arXiv:2610.23172v1 Announce Type: new Abstract: Zero-shot anomaly detection (ZSAD) aims to detect anomalies in previously unseen classes using auxiliary images, with applications such as industrial v...
arXiv:2610.23416v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) have significantly advanced instruction-driven perception through the "Embedding-as-Mask" paradigm. However, e...
arXiv:2610.23533v1 Announce Type: new Abstract: Recent image generators exhibit rich visual priors that can support dense visual perception. However, existing approaches typically encode multiple per...
arXiv:2601.01865v2 Announce Type: replace Abstract: With the growing demand for real-time video enhancement in live applications, existing methods often struggle to balance speed and effective exposu...
arXiv:2610. 23565v1 Announce Type: new Abstract: Monte-Carlo Tree Search (MCTS) typically stores only scalar mean estimates, which makes it poorly suited for tail-risk objectives such as conditional value-at-risk (CVaR).
JAXtari is an open‑source, high‑performance reimplementation of Atari 2600 environments that enables massive GPU parallelization. It allows PPO agents to complete 100 M environment steps on a single A100‑GPU in under an hour, far faster than the CPU‑based ALE. Additionally, JAXtari provides object‑centric observations and a flexible modification system, facilitating research into causal modeling, neuro‑symbolic methods, and rapid agent adaptation.
The paper introduces a model‑agnostic framework that lets frozen large language models (LLMs) and vision‑language models (VLMs) learn from deployment experience without retraining. It does so by adding three external expertise components—a Skill for guiding reasoning and tool use, a Knowledge Memory for storing reliable facts, and a Multimodal Knowledge Base for visual examples—and by using a validation strategy that updates only when new cases improve performance without harming past performance. Experiments on six benchmarks with both open‑weight and closed‑source models show up to a 34.2% performance gain on medical tasks, generalization to unseen cases, and transferability to other models and non‑medical domains.
The paper introduces POBF (Paint Outside the Box and Filter), a framework designed to improve visual grounding in data-scarce settings. POBF synthesizes images by inpainting outside the bounding box to correct label misalignment and employs a filtering scheme that balances hardness and overfitting scores to select the most effective training data. Experiments on four benchmark datasets show that POBF consistently boosts performance, achieving an average 5.83% gain over real-data-only baselines and surpassing leading methods by 2.29%–3.85% in accuracy, while also demonstrating robustness across different generative models, data sizes, and architectures.
The paper introduces MissARF, a new imputation technique that uses adversarial random forests (ARF) for density estimation and data synthesis. MissARF can perform both single and multiple imputations by sampling from the conditional distribution estimated by ARF, conditioned on observed values. Experiments show that MissARF achieves imputation quality comparable to leading methods while offering faster runtimes and no extra cost for multiple imputations.
The paper presents a probabilistic framework for two main test‑driven code generation paradigms: selecting code after generation using an execution environment, and generating code conditioned on environment feedback. It formalizes selection heuristics as environment‑aware estimators of code correctness, proving that fuzzy functional similarity estimators provide a stronger inductive bias and higher signal‑to‑noise ratio than functional equivalence estimators. Additionally, it models backprompting as an in‑context approximation of Thompson sampling, deriving a regret bound that explains its limitations due to ambiguous task descriptions, and validates these theoretical insights with experiments on seven open‑weight models across multiple benchmarks, including a new quantum programming benchmark.
The paper questions whether Theory of Mind (ToM) benchmarks truly assess theory of mind or merely test parsing and algorithmic state tracking. It introduces PDDL-Mind, a neuro‑symbolic method that parses narratives into the Planning Domain Definition Language (PDDL) and executes candidate actions using predefined update algorithms, yielding program‑verified state traces. Experiments on MMToM, MuMA, and FanToM show that delegating parsing to programs and state tracking to PDDL significantly improves performance, suggesting that current benchmarks mainly penalize unreliable implicit state tracking rather than genuine belief or counterfactual reasoning.
MOSAIC is a sparse temporal variational autoencoder that merges causal representation learning with support recovery to identify interpretable latent modules in scientific time series. It leverages regime‑conditioned temporal variation to discover latent variables and uses an additive decoder to recover a sparse set of observations linked to each latent, providing module‑level interpretability. The method offers theoretical guarantees for ANOVA main‑effect identifiability under smooth mixing functions and demonstrates empirical success across diverse domains such as RNA dynamics, solar wind, ENSO climate, industrial process control, and synthetic tokamak data.
arXiv:2610.23707v1 Announce Type: new Abstract: A multi-step agent task fails when a single tool it needs is missing, yet the tools an agent may need are too many to list: the roughly 8,200 tools on...
arXiv:2610.23302v1 Announce Type: cross Abstract: Spatial context prediction requires visual grounding and spatial reasoning to identify vacant regions relative to objects in a scene. Spatial relatio...
arXiv:2603.12507v3 Announce Type: replace Abstract: We consider minimising a spectral risk objective, the expected cost plus a weighted conditional value-at-risk, when the distribution of the uncerta...
arXiv:2507.22075v2 Announce Type: replace Abstract: In unsupervised adaptation for vision-language models such as CLIP, pseudo-labels derived from zero-shot predictions often exhibit significant nois...
arXiv:2610.22832v1 Announce Type: cross Abstract: Expressive speech synthesis can now change emotion within a single utterance, yet its impact on deepfake detection remains unclear. We introduce EmoS...
arXiv:2610.23588v1 Announce Type: cross Abstract: Medical Vision-Language Models (Med-LVLMs) have shown strong performance in Medical Visual Question Answering (MVQA), yet they may still produce fact...