New
Everything new in AI as it appears: launches announced by the labs, brand-new models, datasets, papers and open-source tools. Checked every minute or two. Launches feed · Trending · News
Live now
- Connecting…
Sunday 18 October
- PaperViMoLa: Discrete Motion Tokens for Language-Guided Video Generation
Language-guided video generation often captures scene content while missing the requested motion. We present ViMoLa (Video Motion Language), which predicts a motion prior
- PaperDistributionally-Robust Policy Learning with Observational Data
Policy learning from observational data is fundamental to applications ranging from personalized medicine to welfare-program targeting, but standard approaches optimize e
- PaperDivergence based Ranked Preference Alignment for LLMs
Alignment of large language models typically relies on pairwise preference feedback, though ranked feedback can capture more comprehensive information across multiple res
- PaperAssertion and Belief: Moore's Paradox in Language Models
Moore's paradox \citep{moore1942} concerns sentences such as ``It is raining, but I don't believe that it is,'' which may well be true yet cannot be sensibly asserted. Th
- PaperCVTA: Cross-Variable Temporal Attention for Multivariate Irregular Time Series Prediction
Irregularly sampled multivariate time series arise in many real-world domains such as healthcare, climate science, and large-scale monitoring systems. Characterized by as
- PaperSharp Degree Bounds for Putinar Certificates in Terms of the Positivity Margin via Analytic Sums of Squares
We establish sharp degree bounds for Putinar sum-of-squares (SOS) certificates in terms of the positivity margin $δ$. For any fixed Archimedean quadratic module with pres
- PaperFinite Interaction Lens: Structured Precision Sharing for Vision-Language Models
Identifying which visual interventions interact in a vision-language model requires comparing their joint and separate effects. The resulting four-output difference can b
- PaperBenchmark for Structured Retrieval-Augmented Generation in Perovskite Photovoltaics
While retrieval-augmented language models increasingly serve as literature assistants in the physical sciences, existing benchmarks evaluate them primarily on qualitative
- PaperRepresentations in Motion: Layer-wise Rotation and Trajectory Divergence in LLMs
Recent work suggests that activation dynamics--how representations change during inference--might be more revealing about language model behavior than static readouts fro
- PaperDiffGround: Semantic Difference-Guided Zero-Shot Video Question Grounding
Video Question Grounding (VideoQG) requires both accurate question answering and precise temporal localization. Existing supervised methods rely on costly temporal annota
- PaperDesign and Cross-Domain Evaluation of an Agent Execution Harness
Completing complex tasks with language-model agents requires coordinating planning, execution, and review so the final result addresses the user's original objective. We
- PaperFlattening Fantasies: Analyzing Stereotypes in Pornographic Discourse
This study presents a large-scale quantitative analysis of 5.4 million video titles from xHamster, the world's fourth most visited pornography platform, to examine lingui
- PaperConcurrent two-scale topology optimization of printable bone scaffolds via rectified-flow generation and exact latent-space refinement
Bone scaffolds must reconcile a macroscale mechanical response with microscale geometric feasibility, yet conventional approaches to their design restrict attainable cons
- PaperLearning Which Device to Call: Online Tool Grounding for LLM Agents in IoT
The Internet of Things (IoT) gives large language model (LLM) agents access to physical observations, but one requested capability is usually offered by several devices,
- PaperFTFM: Factorized Tabular Foundation Models
Tabular foundation models (TFMs) are becoming a powerful alternative to conventional tabular learning, adapting to new datasets in context without task-specific training.
- PaperTricking Synthetic Image Detectors with Amortized Generative Attacks
Rapid advances in image synthesis have increased the need for reliable synthetic-image detectors, yet their robustness to transferable attacks remains incomplete and unde
- PaperNarrow Decision Models: A System-1 Architecture for Calibrated, Typed Decisions
System One models, introduced with TypeSafe's Jev, answer typed questions about a state with calibrated probabilities instead of generated text: choosing among options de
- PaperSymbolic Constraint Agents: Mining Formal Tool-Call Constraints to Prevent Agent Errors
Symbolic constraints (programmatic, deterministic checks for tool calls) enable deterministic verification of LLM agents' tool calls, but existing approaches primarily en
- PaperStreamAhead: Real-Time Streaming Video Question Answering via Adaptive Precomputation
Real-time streaming video question answering with vision-language models must answer queries that arrive at any time with low latency while sustaining the video-processin
- PaperEditing as Language: Teaching LLM Agents a Grammar for Native Context Editing
A synopsis in novels folds a story into a few lines; a function in code gathers many steps with a single execution. Context editing is native to language itself. In this
- PaperEmotiQ: A Quantum Residual Specialist Framework for Text Emotion Classification
Emotion classification from text is challenging because many affective states are distinguished by subtle linguistic signals and semantically overlapping boundaries. We i
- PaperBeyond the record: evaluating probabilistic AI weather forecasts deep in the tail
Can probabilistic artificial intelligence (AI) weather forecasts retain skill beyond their training domain? We compare four state-of-the-art AI models (ArchesWeatherGen,
- PaperReinforcement learning on the EPRI AI-ccelerating Unit Commitment benchmark: diagnosing over-commitment and guiding MILP with learned policies
Reinforcement learning (RL) is increasingly proposed as a fast solver for unit commitment (UC), but standalone agents remain far more expensive than mixed-integer linear
- PaperAuditing Tool Traces in Agentic LLMs: Source Localization and Counterfactual Dependence Testing
Agentic LLMs increasingly support scientific prediction by grounding decisions in external evidence. In biology, they promise accurate, interpretable predictions for impo
- PaperNeural Networks with Differentiable Belief-Function Layers
Yager's 1987 rule of combination $\boxplus$ was proposed on epistemic grounds: under high conflict, mass should be redistributed to ignorance rather than renormalised ont
- PaperResidential Construction Image Dataset Using CSI Divisions for Deep Learning-based Object Detection
Accurate recognition of construction site elements is essential for the application of deep learning (DL) in the construction industry. Despite rapid advances in computer
- PaperModaliff: A Unified Token Diffusion Model for Any-to-Any Generation
Any-to-any generation seeks a single model that translates flexibly among text, image, and audio, yet existing approaches either require fully aligned multimodal tuples o
- PaperHow Far Can the Gemma 4 Speech Encoder Go Without Changing Its Weights? Saudi and Gulf Arabic Speech Recognition with a Frozen and an Adapter-Augmented Encoder
We study the 305M-parameter audio encoder shared by Gemma 4 and EmbeddingGemma 2 (bit-identical to that of Gemma 4 E2B except for the final audio-embedding projection) fo
- PaperFrom Clinical Risk Prediction to Operational Decisions: An Uncertainty-Aware Framework for ICU Staffing
Advances in electronic health records (EHR) and large-scale critical care databases have enabled the development of machine learning models for the early detection of pat
- PaperStopLoss: Teaching Agents to Predict Failure and Stop Early
Coding agents keep working on runs that will fail verification, and asking a frontier model to watch for this is expensive in its own right. We introduce StopLoss, a smal
- PaperBreaking the 1/3 Barrier for Approximate Nash Equilibria in Symmetric Bimatrix Games
We give the first unconditional family of polynomial-time algorithms that breaks the $1/3$ approximation barrier for symmetric bimatrix games. For every fixed $δ>0$, an a
- PaperFracTS: Hierarchical and Autoregressive Time Series Generation
Time series are ubiquitous across different domains, and the growing use of synthetic data for privacy-preserving sharing, data augmentation, and stress testing makes tim
- PaperWhen Empathy Misses the Goal: A Benchmark for Goal Displacement in LLM Advice
Conversational large language models can respond with warmth and reassurance while failing to advance the user's stated goal. We conceptualize this failure as $\textbf{go
- PaperATEST: Adaptive Resource-Aware Test-Time Scaling for LLM Inference
Test-time scaling (TTS) improves large language model (LLM) reasoning by sampling multiple answers, but fixed sampling budgets ignore both query difficulty and the changi
- PaperTransformers Learn Two Competing Sorting Algorithms, and Only One Length-Generalizes
We show that two-layer transformers trained to near-zero loss on a sorting task converge to one of two mechanistically distinct solution classes depending on their initia
- PaperReDT: Resolution-Decoupled Visual Geometry Transformer
We introduce ReDT, a feed-forward visual geometry transformer designed to scale multi-view reconstruction to high-definition (HD) inputs. Existing visual geometry transfo
- PaperBud ContextCompact 2.0: Context Compaction for Agent Success and Accuracy with Small Language Models and Constrained Context Windows
Agents that work for many turns outgrow the context window of the model that serves them, and on small language models (SLMs) and constrained inference systems that windo
- PaperWhen Interpretations Persist: Downstream Influence in Gaze-Aware Assistants
AI assistants may carry forward not only observations but also interpretations of what a person is doing or may do next across time. Once retained, these interpretations
- PaperDynamics-Aligned Representation Learning under Induced Partial Observability
Model-based reinforcement learning (MBRL) has enabled sample-efficient learning of continuous control policies from high-dimensional observations through learned latent d
- PaperKPI-Aware Multimodal Anomaly Detection for 5G and Open RAN Telemetry
Reliable anomaly detection is a deployment bottleneck for 5G/Open RAN observability and emerging self-optimizing 6G systems, where hundreds of heterogeneous KPIs, severe
Headlines and links come from the labs' own blogs, Hacker News and the GDELT news index, and from the sources our index already follows. We show a short excerpt and always link to the original. A launch reported by a news site rather than the lab is marked “Reported” until the lab itself announces it.