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…
Monday 19 October
- PaperFunctional Cross-layer Experts Routing for One-step Diffusion Distillation
One-step distillation compresses diffusion trajectories into a single forward evaluation, yet how internal capacity should be structured within that remaining pass remain
- PaperHow Much Does One Wrong Answer Cost? Error Propagation in Constraint Pruning with Noisy LLM Oracles
Constraint pruning saves queries to a large language model (LLM) or another noisy oracle by skipping each yes/no question implied by answers accepted earlier, for example
- PaperA Calibrated Instrument for Detecting Disposition Drift in Language Models
Before language models are released, they are tested for harmful traits such as willingness to carry out dangerous requests, deception, power seeking, and sycophancy. The
- PaperThink Densely, Act Sparsely: Latent Expert Cognitive Chains for Vision-Language-Action Autonomous Driving
Autonomous driving fundamentally demands dense understanding of visual, semantic, and geometric information, yet existing Vision-Language-Action (VLA) models are typicall
- PaperTimelineAgent: An LLM-based Framework for Query-Centric Event Timeline Extraction Across Multiple Documents
Query-centric cross-document event timeline extraction aims to construct event timelines from multiple documents under diverse query focuses. The task is very challenging
- PaperDoes Unlearning Survive Collaboration? Robust Unlearning for Shared-Model LLM Teams
LLM unlearning is essential for removing sensitive or unwanted knowledge while preserving useful capabilities. As LLM teams are increasingly used to solve complex problem
- PaperNeural Video Coding under Limited Delay: Theoretical Optimality and System Design
Traditional neural video compression (NVC) methods predominantly follow strictly causal predictive-coding paradigm, treating zero-frame delay as a fixed constraint rather
- PaperNo Matter Who You Are: Addressivity and Sycophancy in Large Language Models
Sycophancy, where an LLM becomes overly agreeable, deferential, or flattering toward the user, has been identified as a major failure mode. While post-training has been i
- PaperAnatomy of Off-Policy Policy Gradient: Importance Sampling, KL Regularization, and Baselines
Reinforcement learning has become a central tool for large language model (LLM) post-training, where policy gradient methods are routinely deployed off-policy, even thoug
- PaperInside the Scorer: Mechanistic Evidence on Rubric Control in LLM-Based Automated Essay Scoring from 25 Base Models
Automated essay scoring (AES) using large language models (LLMs) offers promising use cases for language assessment, yet high-stakes testing requires scores that are both
- PaperLearning to Couple: Context-Adaptive Joint Denoising for Diffusion Language Models
Diffusion language models accelerate generation by predicting multiple tokens in parallel, but factorized denoisers treat simultaneous predictions as conditionally indepe
- PaperCorrected Block Sparse Spectral Optimization: Exact Models, Finite Identification, and Local Dynamics
The block generalized-power method pairs threshold-based support selection with inexpensive Stiefel updates, but the standard block formulation conflates two nonequivalen
- PaperFine-Grained Units, Flat Decisions: Hierarchical Micro-Expert Pruning for Mixture-of-Experts Models
Micro-expert pruning reduces the capacity of mixture-of-experts (MoE) models by removing coupled channels within routed experts. However, finer pruning granularity alone
- PaperLEVI: Benchmarking Visual Identity Fidelity with Verifiable Low-Entropy Constructs
Modern generative models can produce visually plausible images while violating exact identity constraints. Evaluating such failures requires distinguishing violations of
- PaperPFedQFT: Personalized Federated Quantum-Inspired Fine-Tuning for Medical Large Language Models
Medical data remain fragmented across institutional silos because of privacy, governance, and ownership constraints. Federated learning enables medical institutions to ad
- PaperEvidence Sufficiency and Model Comparisons in MexRegQA: An Item-Level Audit of Mexican-Spanish Regulatory QA
Similarity-gated coverage does not establish that retrieved evidence contains the facts needed to answer a question. We audit Mexican-Spanish financial-regulatory QA and
- PaperCausal Humility: Governing the Authority of Fairness Claims Under Causal Uncertainty
AI systems increasingly shape consequential decisions in employment, lending, healthcare, and public services, making fairness an important problem for auditing and gover
- PaperWhose Credential Is It? How Owner Attribution in Agent MemoryShapes Cross-User Account Misuse
Shared long-term memory lets an LLM agent serving one user inadvertently retrieve another user's credentials, but it is unclear when such exposure leads to actual harm. W
- PaperPredictive Bandit Curriculum Reinforcement Learning via Gradient-Based Sample Group Discovery
Curriculum learning, which organizes training samples according to their learning priority, has been widely adopted in reinforcement learning to improve training efficien
- PaperFrom Black Box to Controller: Inference-Time Steering of LLM via Feature Amplification
Inference-time steering is crucial for deploying Large Language Models (LLMs) in real-world applications, where they must flexibly adjust behavior preferences. For instan
- PaperStochastic Tracking of Drifting Affine Fixed Points
Linear stochastic approximation (SA) is widely used to estimate fixed points from noisy observations, but most finite-time analyses assume that the underlying operator re
- PaperCVaR-RMD: CVaR Selection Pressure for Robust Metaheuristic Discovery
Large language models have recently been used to discover heuristics through iterative program search, offering a promising approach to automated algorithm design. Howeve
- PaperMulti-View Structural Representations for Physically-Consistent TeX Generation
Infrared and visible images provide complementary cues for low-light image generation, and physics-based methods can better exploit this complementarity. However, existin
- PaperToolOPD: Credit-Aware On-Policy Distillation for Tool-Use Agents
On-policy distillation (OPD) enhances the capabilities of small language agents by providing dense, token-level supervision from a teacher model on student-generated traj
- PaperProgress-Guided Preference Generation for Aligning Generative Control Policies
Generative policies have achieved strong performance in imitation learning tasks, but their success is often constrained by the limited availability of expert demonstrati
- PaperMT-CC: Multi-Group Temperature Scaling for Asymmetric Calibration Behavior in Class-Incremental Learning
As deep neural networks are required to continuously adapt to evolving data, class-incremental learning (CIL) has become an active research area. However, most existing w
- PaperWhen Safety Fails Collectively: Robust Alignment Against Harmful Fine-Tuning via Joint Weight Perturbations
Harmful fine-tuning can rapidly erode the safety alignment of large language models, creating substantial risks when aligned models are adapted to downstream tasks. Exist
- PaperBitFlat: Error-Localized Bitstream Design for Robust Diffusion Image Compression
Zero-shot diffusion image compression based on reverse channel coding achieves high perceptual quality at low bitrates without retraining, yet its bitstream remains vulne
- PaperRxGS: Relightable Gaussian Stylization via BRDF Decomposition
Reference-based 3D scene stylization transfers the appearance of a reference image onto a reconstructed 3D scene while preserving scene geometry. Recent methods perform t
- PaperLOOP: Recovery-Aligned Iterative Layer Pruning via On-Policy Distillation
Layer-level pruning is attractive for large language model (LLM) deployment as it reduces the model size while preserving a dense architecture that can be efficiently exe
- PaperCross-Pollination Retrieval: Finding Transferable Ideas Across Fields in Scientific Literature
Many scientific advances come from cross-pollination, carrying an idea from one field over to a problem in another. Yet retrieving papers across fields remains underexplo
- PaperNeither Over- nor Under-Constrained: Evaluating LLM Personalization under a Constraint Qualification Audit
Accurate evaluation of LLM personalization is hindered by current evaluation paradigms that over- or under-constrain the response space, yielding frequent false rejection
- PaperLIRQuant: An Efficient Locally Isolated Rotation Quantization Method for Large Language Models
Post-Training Quantization (PTQ) enables efficient deployment of Large Language Models (LLMs), yet activation outliers remain a key challenge for low-bit quantization. Ex
- PaperHyperTaxa: Multiscale Genome Representations for Generalized Microbial Taxonomic Inference
Reliable microbial taxonomic inference is challenged by the rapid growth of newly sequenced organisms and incomplete reference coverage. While alignment- and database-dri
- PaperArbitrage-Free Implied Volatility Surface Reconstruction via Additive Martingales
This work focuses on reconstructing a continuous implied volatility (IV) surface from a small number of option quotes, a fundamental task for option pricing and risk mana
- PaperFrechet Forcing: Training Long-Horizon Streaming World Models from Short Clips
Streaming video world models generate the future chunk by chunk, conditioned on their own past and a stream of actions. Trained on short clips, they drift once a rollout
- PaperSpaRV: Sparse Radiance Voxels for Scalable Geometrically Consistent LiDAR-Visual Mapping and Rendering
Robotic simulation, navigation, and inspection need photorealistic and geometrically accurate maps. Radiance fields achieve photorealism, but building them from robot dat
- PaperPoSTCache: From Forecasting to Postdictive Smoothing for Revisable Diffusion Caching
Diffusion and flow matching models achieve impressive visual generation quality but remain computationally expensive due to iterative sampling. Caching-based acceleration
- PaperCan Metadata Fix the Gauge? Calibration Turns Sparse Multi-Source Learning from Sparse PCA into Sparse Mean Recovery
Source labels tell us where a sample came from, but not how that source oriented its coordinates. In a sparse Gaussian multi-source model with source-specific sign gauges
- PaperKnowledge Manifold Optimization for Scientific Discovery
The rapid expansion and specialization of scientific literature make it increasingly difficult to identify not only what is known, but where new and still supportable kno
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.