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…
Yesterday
- PaperDynamical Batching: How Class-Cycling Training Shapes the Internal Structure of Neural Networks
We investigate whether cyclically varying the class composition of training batches can modify both the performance and the internal organization of neural networks. Moti
- PaperDeepSEA: A Multilingual Evaluation Benchmark for Southeast Asia
While language models have demonstrated remarkable capabilities, their performance remains disproportionately skewed towards high-resource languages. This disparity is pa
- PaperPhysics-Driven Framework for QoS-Constrained Satellite System with Non-Linear PA Distortion
This work develops a physics-driven self-supervised graph learning framework that directly optimizes the distortion-aware precoder under nonlinear correlated power amplif
- PaperFLMNet: Self-Ensemble Distillation from Masks to Seeds for Single-Tower CTR Prediction
Click-through rate (CTR) prediction underpins recommender systems and online advertising, where high-dimensional categorical features interact in combinatorially many way
- PaperReinforcement Learning Controllers for Fusion Scenario Development
Scenario development, the design of the waveforms that take a tokamak discharge from breakdown to flat-top, is still an iterative, labour-intensive process. Every candida
- PaperNash-MOPD: Optimizing Task Trade-offs in Multi-Teacher On-Policy Distillation
Multi-teacher on-policy distillation (MOPD) aggregates the capabilities of multiple domain-expert teachers into a single student model. However, all domains in MOPD share
- PaperOptimal Multi-Kernel Combination for Online Multi-Label Classification
Multi-label classification is particularly challenging in streaming scenarios, where data arrives sequentially. Online kernel methods offer a promising solution. However,
- PaperVariance-Aware Non-Stationary Bandits:All-Budget Regret Bounds and Adaptation Costs
Low reward variance reduces estimation cost, but does not eliminate monitoring of arms that may improve while unobserved. We refine the variance--variation tradeoff and c
- PaperFrom Retrieval to Recognition:Knowledge-Enhanced Post-training of Time Series Foundation Models for Classification
Time series foundation models (TSFMs) have achieved notable progress in classification tasks through large-scale pretraining. However, their post-training practice mainly
- PaperDon't Rewrite the SID Map: Topology Preservation for Generative Retrieval in Dynamic E-Commerce Search
Generative retrieval assigns each item a discrete semantic identifier (SID) and retrieves items by autoregressively generating SID sequences. In dynamic environments such
- PaperDeclarative Explanations for Graph Neural Networks: A Demonstration
Graph Neural Networks (GNNs) have proven effective for graph analytical tasks, yet their "black-box" nature complicates the understanding of their layer-wise behavior and
- PaperLearning from a Bandit Learner
Classical inverse bandit methods typically aim to recover true reward parameters. In contrast, we infer a demonstrator's subjective beliefs, specifically its internal est
- PaperProvable Adversarial Detection: Prime Quantization meets Gromov--Wasserstein
Adversarial vulnerability persists across modern vision architectures from CNNs to vision language models (VLMs), yet existing detection methods rely on heuristics withou
- PaperReliable Before Profitable: QuantHarness for Governing Financial Strategy Development with LLM Agents
LLM agents can turn natural-language financial research requests into executable and backtested strategies, but a successful run may still implement the wrong rule, use i
- PaperMultilingual Voicemail and Answering Machine Detection via Pretrained Audio Embeddings and Gradient Boosting Machines
Answering machine detection (AMD) is a fundamental task in telephony that classifies whether an answered call is picked up by a human or a voicemail (machine). Despite it
- PaperFrom Code to Playable Systems: CEGame-Bench for Long-Horizon Game Creation Agents
A game ships when a player can launch it, finish it, and return to a saved world, none of which a successful build guarantees, yet game-creation agents are mostly tested
- PaperPnP-Transformer: A Neural Pose Solver for 6D Object Pose Estimation
We present PnP-Transformer, a neural pose solver designed as an iterative-free, differentiable alternative to classical PnP-RANSAC algorithms. PnP-Transformer regresses t
- PaperHow Robust Are Prognostic Radiomic Features? Comparing Selection Techniques on Pooled Glioblastoma Cohorts
Radiomic survival studies in glioblastoma report heterogeneous prognostic features, but how much of this stems from the methodology itself is rarely examined. We analysed
- PaperGeoNaviDiff: Transferring Disentangled Semantic Controls to Diffusion Features via Local Riemannian Navigation
Disentangled real-image manipulation requires factor-specific semantic control while preserving image fidelity and non-target content. StyleSpace $S$ provides interpretab
- PaperRGB--Event Object Detection Across Operating Frequencies via Reliability-Supervised Routing and Asymmetric-Resolution Fusion
Autonomous vehicles must detect objects faster than a frame camera delivers images. Event cameras record brightness changes with microsecond resolution, so RGB--event det
- PaperLeakBench: Auditing Reward Hacking through Prediction-Time Leakage in Clinical Modeling Agents
Autonomous clinical-modeling agents can optimize predictive performance while violating conditions that make a model usable. We introduce LeakBench, an executable, guidel
- PaperContext-Aware Topological Distillation Graph Network for Asymmetric EEG-Eye Movement Emotion Recognition
EEG-eye movement emotion recognition can support mental-health monitoring and adaptive interfaces, but most fusion models treat the two signals as parallel features, clas
- PaperDeOverlay: A Benchmark and Source-Anchored Flow for Video Overlay Removal
Video overlay removal aims to recover scenes obscured by subtitles, titles, and logos while preserving surrounding content. Existing methods use temporal propagation or s
- PaperToolkit for Facial Deidentification
This work presents a novel open-source toolkit designed for the evaluation of face deidentification techniques with available evaluation models. The framework provides a
- PaperDCR-TSF: Dual-Level Compositional Reasoning with Triadic Spherical Fusion for Training-Free Zero-Shot Composed Image Retrieval
Zero-shot composed image retrieval (ZS-CIR) aims to retrieve a target image that reflects an intended textual modification while maintaining semantic consistency with a r
- PaperNot All Similarity Is Leakage: Distribution-Aware Identity Leakage Assessment in Synthetic Face Datasets
Synthetic data provides the means for more ethical and less biased facial recognition. Nonetheless, the limitations of generative models and the conditioning process they
- PaperCUA-Lite: An Open Platform for Computer Use Agents
Open resources for computer use agents (CUAs) -- environments, datasets, and models -- remain scattered: without a standard, these resources cannot be integrated and scal
- PaperRisk Decomposition for Hallucination-Aware Video Sampling
Despite achieving high visual fidelity, video models still suffer from physical hallucinations, limiting their reliability as world simulators. Existing methods leverage
- PaperPhysSkin++: Real-Time and Generalizable Physics-Based Animation via Self-Supervised Neural Skinning
Generalizing real-time physics-based animation across diverse 3D shapes and spatial discretizations remains challenging. In this paper, we introduce PhysSkin++, a physics
- PaperFinSafeGuard: A Quality-Driven Synthetic Dataset for Financial AI Safety
Generating high-quality synthetic datasets at scale remains a fundamental challenge for training specialized AI systems in data-scarce domains. We present a comprehensive
- PaperLearning the Dose Manifold: A Latent Diffusion Framework for Volumetric Dose Prediction in Automated Radiotherapy Treatment Planning
Automated treatment planning (ATP) aims to reduce the unwarranted inter-planner variability of manual planning, while improving treatment quality and efficiency. Most ATP
- PaperProcedural Exposure Bias in Skill-Augmented Language Model Agents
External skills provide language-model agents with reusable procedural knowledge, yet how models use such knowledge after it is supplied remains poorly understood. We ide
- PaperHoneyed Words, Hidden Daggers: Benchmarking and Training LLMs to See Through Mock Politeness
The Chinese idiom "kou mi fu jian" ("honeyed words, hidden daggers") names speech that is polite in form but hostile in function. We present ZhenhuanBench, a 1,592-item b
- PaperAVTime: Reinforcing Dense Audio-Visual Captions with Bidirectional Alignment
Dense temporal audio-visual captioning is important for multimodal video understanding and generation. However, prior work is constrained by three main limitations: (1) t
- PaperBalance-Aware Pivot Selection for Parallel Diffusion LLM Decoding
Diffusion language models enable parallel token generation, offering a promising alternative to sequential autoregressive decoding. Existing acceleration methods use pred
- PaperFinHopper: A Progressive Multi-Hop Benchmark for Complex Financial Agents with Step-wise Evaluation
Financial agents are expected to answer factual investment queries through open search, but financial multi-hop retrieval differs from general multi-hop QA in a crucial w
- PaperDecision4Rec: A Jev-Inspired Framework of Decision Models on Knowledge and Active Graphs for Multi-Agent Recommender Systems
Decision models, such as the commercial Jev, are language models that return one probability for each option of a question instead of generating text. We present Decision
- PaperAuDQ: Auditable Data Quality through Agentic Rule Discovery
High-stakes tabular pipelines rely on scattered, static quality checks that are hard to evolve and audit against policy intent. Regulated domains particularly suffer as t
- PaperTruncate or Not? A Scaling Study of Looped Transformers with Truncated Backpropagation
Looped transformers reuse a shared block of layers to increase computational depth without increasing the number of trainable parameters. They are trained with backpropag
- PaperTowards instance-dependent regret optimality in Episodic MDPs with Posterior Sampling
We study regret minimization in finite-horizon episodic Markov Decision Processes (MDPs). While minimax-optimal algorithms are known, tractable approaches to instance-dep
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.