OpenAI Blog
Sep 9
The AI policy window is open. We need to act.
Chris Lehane argues that as AI capabilities grow, we must strengthen safety evidence, adopt shared standards, and take durable policy action while the policy window remains open.
AI safety and alignment
Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
Hugging Face Trending Papers
Sep 9
Beyond Training: A Feasibility Taxonomy for Inference-Time AI Governance
Compute governance today is a governance of training: the thresholds, reporting requirements, and frontier-AI regimes now in force attach to training compute and treat the trained model as the regulat...
Hugging Face Trending Papers
Sep 9
Deterministic Prompting for Speaker-Stable Low-Resource Greek TTS
Modern TTS systems approach human quality for high-resource languages but degrade when clean speech data is scarce. Modern Greek exemplifies this, lacking the curated corpora behind state-of-the-art s...
Hugging Face Trending Papers
Sep 9
Can We Trust Video Hallucination Detectors? VidHalLoc for Evaluating the Evaluators
Video-language models and video agents can produce hallucinations that conflict with spatiotemporal evidence. Existing benchmarks mainly evaluate model hallucinations, and heterogeneous mechanisms mak...
Hugging Face Trending Papers
Sep 9
StreetDiff: Multi-view Street Scenes Generation via Cross-view Consistent Multi-view Stable Diffusion with Structure Prompts
Multi-view diffusion models have shown strong performance in scenes with strong geometric priors and sparse semantics, such as indoor rooms or simple outdoor environments (e.g., fields, courtyards). H...
Hugging Face Trending Papers
Sep 9
When Does Defendant Statement Matter? A Study of Bias and Persuasion in LLM-Simulated Jurors
LLMs have been used to simulate human decision-making in professional settings, yet their behaviors in common-law jury trials remain unexplored. We study when and how a defendant's courtroom statement...
Hugging Face Trending Papers
Sep 9
Morphological Decoupling-Based Skeletal Classification for Clinical Assessment of Malocclusion
Malocclusion skeletal grading is a fundamental task in orthodontics, critical for diagnosis and treatment planning. Traditionally, cone-beam computed tomography (CBCT) is used for visual measurement,...
Hugging Face Trending Papers
Sep 9
LogiScope-VQA: Benchmarking Vision-Language Models for Logistics Hazard Identification in Industrial Scenarios
Large Multimodal Models (LMMs) large-scale deployment in industrial warehouse settings specifically necessitates that models exhibit human-expert-level hazard-oriented perception, understanding, and r...
Hugging Face Trending Papers
Sep 9
BRACE: Anchored Bellman-Residual Correction for Stale Critics in Asynchronous RL
Asynchronous reinforcement learning has become the standard way to scale training for language models, but the resulting policy lag biases the critic toward the stale behavior policy. Existing work on...
Hugging Face Trending Papers
Sep 9
Procedural Memory Under Change: Reuse and Interference in Controlled Web Tasks
Procedural memory lets language agents reuse successful routines, but reuse presumes that a stored routine remains applicable. We study what happens when that presumption is deliberately violated. The...
Hugging Face Trending Papers
Sep 9
LexAgentHallu: A Hierarchical Benchmark for Profiling Hallucinations in Legal Agents
As large language models are increasingly deployed as tool-augmented legal agents, they introduce agentic hallucinations where tool-call and reasoning errors cascade into fabricated holdings and misci...
Hugging Face Trending Papers
Sep 9
StreamAlign: Streaming Text-Aligned Speech Tokenization
Text-aligned speech tokenization methods have emerged to better align speech tokens with LLM token spaces, enabling more effective utilization of pretrained LLMs. However, they rely on offline automat...
Hugging Face Trending Papers
Sep 9
Compact Visuotactile World Models for Lifting: Prediction, Reward Alignment, and Force Constraints
Accurate contact prediction is useful for robotic manipulation only if it supports effective decisions. We investigate this connection using a compact, randomly initialized visuotactile world model, t...
Hugging Face Trending Papers
Sep 9
Modality-Decoupled Federated Learning for Privacy-Preserving Embodied Intelligence in 6G
Sixth-generation (6G) wireless networks are expected to provide a key infrastructure for large-scale embodied intelligence, where heterogeneous robots collaborate through low-latency connectivity, edg...
Hugging Face Trending Papers
Sep 8
NOAH: Learning the Full Patient Journey. A Longitudinal Multimodal Time-Aware Model for Representation and Forecasting
NOAH is a generative transformer that models the entire multimodal patient journey by integrating bidirectional time and a variational latent space to capture continuous, stochastic clinical trajectories. Trained on over 559 million events from 431,000 hospital visits, it processes medical images, time‑series, numeric signals, categorical events, and both structured and unstructured records. The model supports autoregressive forecasting, zero‑shot classification, and counterfactual simulations, yielding strong predictive performance across 15 ICD chapters, 29 comorbidities, and time‑to‑event outcomes.
Hugging Face Trending Papers
Sep 8
Nearly Tight Rademacher Bounds for Sparsely Activated Neural Networks
An input may activate few hidden units even when different inputs collectively use an entire network. We study the statistical complexity of this input-dependent sparsity in the one-hidden-layer ReLU model of Awasthi et al.
Hugging Face Trending Papers
Sep 8
Everything in Moderation: Per-Domain Coverage Optima and Alignment-Resistant Domain Gaps in Multi-Domain Mid-Training
The paper investigates how per-domain data composition during the mid‑training phase (between pre‑training and alignment) affects model performance. Experiments with Qwen3‑8B‑Base across five KOR‑Bench domains show that a moderate coverage band (10%‑40%) yields the best performance for each domain, and that alignment passes cannot fully close the gaps created by suboptimal mid‑training allocations. Additionally, zero coverage during mid‑training severely degrades accuracy, while a carefully tuned allocation can provide the largest overall pipeline improvement.
Hugging Face Trending Papers
Sep 8
DXPR: Depth-Based Vision-LiDAR Cross-Modal Place Recognition Using Vision Foundation Models
DXPR is a depth‑based cross‑modal place recognition framework that matches monocular camera queries to a LiDAR map using a single vision foundation model backbone. By converting both modalities into a unified depth image representation, DXPR learns modality‑invariant global descriptors without modality‑specific encoders. A geometry‑aware overlap miner refines pairwise metric learning by computing pixel‑level overlap scores, and extensive tests on KITTI and Boreas show strong performance across seasons, weather, and day/night conditions, outperforming prior CMPR baselines.
Hugging Face Trending Papers
Sep 8
GraphFAS: A Distributed System for Automated Graph Feature Generation and Selection in Industrial Transaction Networks
GraphFAS is a distributed system that automates graph feature generation and selection for industrial transaction networks. It uses a non‑parametric graph feature generator that creates explicit, interpretable structural features through multi‑hop subgraph extraction and multi‑scale aggregation, and an extended Boruta algorithm that aggregates feature importance across partitions to robustly identify informative features at scale. By decoupling feature aggregation from model training, GraphFAS can be directly integrated with tabular models and TreeSHAP‑based explanations, and it has been deployed in Alipay, achieving significant engineering efficiency gains and strong performance against expert‑driven and graph‑learning baselines on large‑scale graphs.
Hugging Face Trending Papers
Sep 8
API Benchmark Scores Do Not Reliably Transfer to Chatbot Interfaces
The paper examines whether benchmark scores obtained via APIs accurately reflect the performance of AI chatbots when accessed through user interfaces. By auditing ChatGPT, Claude, and Gemini across seven systems and nine benchmarks, the authors find that API evaluations consistently overestimate accuracy and consistency compared to interface evaluations, with differences comparable to downgrading a full model generation. Attempts to align API behavior with interface behavior through prompt and parameter adjustments only partially close the gap.