Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2609.01575v1 Announce Type: new Abstract: Extracting structured fields from hundreds of millions of documents annually remains costly in regulated industries: bespoke OCR cascades cover only a...
arXiv:2502.16903v3 Announce Type: replace Abstract: Despite the growing interest in jailbreaks as an effective red-teaming tool for building safe and responsible large language models (LLMs), flawed...
arXiv:2609.00369v1 Announce Type: new Abstract: Generating co-speech gestures that are temporally coherent, semantically aligned with speech, and grounded with surrounding objects remains challenging...
arXiv:2609.00505v1 Announce Type: new Abstract: Video-text models adapted from image-text architectures (e.g., CLIP) frequently exhibit temporal blindness, the inability to perceive fundamental cues...
arXiv:2609.00846v1 Announce Type: new Abstract: The rising prevalence of psychological disorders necessitates effective emotion monitoring, yet current methods relying on facial or physiological sign...
arXiv:2609.00955v1 Announce Type: new Abstract: Diffusion models achieve strong image generation quality but incur high iterative denoising costs. Analog compute-in-memory (CIM) can accelerate matrix...
arXiv:2609.01123v1 Announce Type: new Abstract: Recent advancements in low-light image enhancement have leveraged diffusion models for their strong ability to generate perceptually realistic, detaile...
arXiv:2609.01470v1 Announce Type: new Abstract: As AI systems are increasingly used to draft radiology reports, reliably evaluating their clinical quality remains a critical challenge. Large language...
arXiv:2609.01582v1 Announce Type: new Abstract: Complex 3D spatial text to image generation requires models to convert natural language into stable visual geometry, not merely semantic appearance. Ex...
arXiv:2609.01036v1 Announce Type: cross Abstract: A lack of suitable datasets has limited the research into the privacy risks of novel smart city sensors, such as thermal cameras, depth cameras, and...
arXiv:2609.01060v1 Announce Type: cross Abstract: Compact snapshot hyperspectral cameras provide rich instantaneous spectral measurements for ground-level machine vision, but at lower spatial resolut...
arXiv:2609.01306v1 Announce Type: cross Abstract: Triangle-based neural rendering bridges neural scene representations and conventional graphics pipelines by optimizing explicit geometric primitives...
arXiv:2507.22052v3 Announce Type: replace Abstract: We present Ov3R, a novel framework for open-vocabulary semantic 3D reconstruction from RGB video streams, designed to advance Spatial AI. The syste...
arXiv:2601.13913v3 Announce Type: replace Abstract: We consider monocular 3D human pose estimation (HPE), where the goal is to predict 3D human skeletal joints from a single 2D image, typically via 2...
arXiv:2608.01602v2 Announce Type: replace Abstract: Cardiac digital twins convert clinical images into physiological measurements through observation operators, yet calibration studies often assume a...
The paper introduces Conditional Flow Matching (CFM) for engineering inverse design, comparing it to conditional diffusion models and cGANs on EngiBench structural and thermal benchmarks. CFM outperforms the baselines in cumulative and final optimality gaps, mean volume‑fraction deviation, and throughput, achieving up to 66× faster sample generation with fewer network evaluations. The study demonstrates CFM’s effectiveness as a warm‑start generator for gradient‑based refinement in PDE‑constrained design problems.
The paper introduces CRAFT, a data‑centric fine‑tuning approach that aligns small language models (SLMs) for pre‑hoc reasoning in AI‑native 6G radio access networks (RAN). By automatically generating verified (input, trace, label) triplets and fine‑tuning with low‑rank adaptation, CRAFT achieves high accuracy and F1 scores on TRACTOR and IC xApp datasets while avoiding parse failures that plague RL methods like GRPO. It also reduces energy consumption by 59% compared to GRPO baselines, offering a more sustainable path to auditable AI in 6G RAN.
AdaSearch introduces a two‑stage reinforcement learning framework that separates problem solving from the decision to search in large language models. By using an F1‑based decision metric, it explicitly evaluates when external search is needed, reducing unnecessary search calls while maintaining high question‑answering performance. Experiments show that AdaSearch improves search‑decision quality with only a minor impact on accuracy compared to always‑search strategies.
The paper investigates whether large language models (LLMs) can leverage frozen relational‑transformer embeddings by injecting them as soft tokens. Using a learned MLP projection and LoRA adaptation, the authors fine‑tune Qwen3.5‑4B on chain‑of‑thought reasoning traces and group‑based reinforcement learning, then evaluate on ten binary classification tasks across six RelBench databases. The hybrid approach consistently underperforms the standalone relational transformer, showing sensitivity to serialization format, token budget, and RL stability, leading the authors to conclude that stronger alignment objectives and schema‑aware design are needed for reliable relational prediction.
The paper investigates how visual understanding and generation objectives interact within unified multimodal models (UMMs). At the representation level, each objective enriches the other, but forcing them through the same computation path can cause one to dominate; a task‑decoupled architecture mitigates this. At the task and system levels, the authors demonstrate bidirectional transfer between shared knowledge and superior performance of an end‑to‑end UMM over a planner–executor pipeline on complex tasks.