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
- PaperWhere Are Language-Specific Features Represented in Multilingual LLMs? Everywhere
Previous work has argued that multilingual LLMs encode language-specific features most strongly in their initial and final layers, implying that intermediate layers suppo
- PaperFrom Seeing to Reporting: A Theory of Reliable Visual Set Generation in Vision-Language Models
Vision-language models (VLMs) are asked to report what they see: to count objects, box them, parse a screen or pick a click target (GUI grounding). We argue that reportin
- PaperSteered Not Stirred: Effective Reward Tilting using Surrogate Reward Mixing
Continuous-time generative models, from diffusion models, flow matching, and now flow maps, owe their practical value to high-fidelity generation and steerability. In man
- PaperFormal Raising: Embedding Verifiable Ethical Properties into the Development of AI
Alan Turing proposed constructing a ``child machine'' and educating it rather than directly programming an adult-like intelligent machine. Recent work on model raising re
- PaperAssessing the AI Readiness of Construction Datasets: A Multidimensional Operational Framework
The rapid growth of artificial intelligence (AI) applications in construction has increased the demand for datasets suitable for reliable model development, evaluation, a
- PaperSelf-Distillation for Supervised Fine-Tuning
Supervised fine-tuning treats the expert demonstration or gold response as a one-hot target, suppressing valid alternative continuations that the model would otherwise as
- PaperFrom Proposal to Execution: Modeling Interaction Semantics in Shared Autonomy
In many human-AI systems, candidate actions are not executed directly but are first evaluated by another decision-making entity under a potentially different objective or
- PaperProbabilistic Limit Order Book Forecasting with Conditional Diffusion Models
Modeling limit order book (LOB) dynamics is central to market forecasting and execution-strategy evaluation. While diffusion models achieve strong empirical performance,
- PaperGroundedVDR: Grounding Video-to-Web Evidence Dependencies in Video Deep Research
Video large multimodal models have improved at identifying cross-frame visual evidence and conducting open-web retrieval, as reflected in recent video deep research (VDR)
- PaperSlimFormer++: Token Mixing Where It Matters for Efficient 3D Medical Image Segmentation
To determine where computation is needed in volumetric segmentation networks, we analyze block-level redundancy and stage-wise token-mixer contribution. Centered Kernel A
- PaperPCXR-Copilot: Device-aware pediatric chest radiographic analysis with segmentation, suppression, and edema-related cues
Patients admitted to pediatric ICU and cardiac ICU often require intensive perioperative support and frequent chest radiography to monitor support devices, extravascular
- PaperPRIMA: Pose Refined Inductive Motion Adapter for Zero Shot Social Bodily Behavior Recognition
Recognizing fine-grained bodily behaviors, such as self-grooming, postural shifts, and backchanneling, is a useful intermediate step for computational social signal analy
- PaperMultimodal-Conditioned Latent Diffusion Models for Spatiotemporal Brain MRI Forecasting
Spatiotemporal forecasting of 3D anatomical changes is a critical generative vision challenge for modeling Alzheimer's Disease (AD) progression. While brain MRI forecasti
- PaperConsistent LLM Call Handling Across Java Frameworks: A Reference Implementation and Benchmark
Java applications reach large language models (LLMs) through an integration framework, and rely on it to handle a failing provider: to retry what can be retried and nothi
- PaperTest-Time Scaling of Text-to-Image Flow Matching Models with Noise-Rejuvenated Sequential Monte Carlo
Test-time scaling of diffusion models with sequential Monte Carlo (SMC) has become a promising strategy for sampling under user-specified rewards, such as human preferenc
- PaperP(Yes): 15$\times$ Improvements via Test-Time Scaling of Decision Models
Decision models answer typed questions, such as multiple-choice or yes/no questions, with a probability for each option. We add test-time search to frozen decision models
- PaperSZED at ArGuard Shared Tasks: Multi-Task Label-Attention and Cross-Modal Fusion for Arabic Hateful Meme Detection
We present SZED's submission to ArGuard 2026 Track A: Arabic hateful meme detection. The task has two parts: binary classification (A1) and fine-grained multi-label taggi
- PaperA failure of Imagination: VLMs fail to use visual representations for text, but self-distillation can help
Vision-language (VL) models are typically built by fine-tuning a language model to attend to visual features in service of a Visual Question-Answering objective. We ask w
- PaperNear-Optimal Last-Iterate Convergence of SGD in the Smooth Interpolation Regime
We study the last iterate of stochastic gradient descent (SGD) with a constant stepsize on smooth convex objectives in the low-noise and interpolation regimes, where the
- PaperOn Reasoning Correctness Directions
We present experimental evidence suggesting that information about whether a model's reasoning is on the right track can be linearly decodable without defining a causally
- PaperDiaLong: Benchmarking Reminiscence in Long-Context Dialogues
How well can transformer-based Large Language Models (LLMs) retain and recall memories in long contexts of dialogue? LLMs are known to forget long-range factual informati
- PaperReliability-Preserving Compression for Deployable Medical Image Segmentation
Post-training compression of pretrained medical segmentation models commonly uses quantization, pruning, or distillation to reduce model size and computational cost. Exis
- PaperBiDex-100: A Comprehensive Benchmark for Bimanual Dexterous Manipulation Across 100+ Simulation Tasks
Bimanual manipulation with dexterous hands has attracted growing attention in research on robotic action models. However, few studies have developed benchmarks specifical
- PaperQuality-Controlled Reply and Summary Data for Post-Training Small Language Models in AI Call-Screening Agents
Small language models have improved to the point where a phone can plausibly screen its own calls, answering on an absent owner's behalf without sending call content off
- PaperSystem X: An LLM Decision Model That Replies from Its Own KV Cache
Decision models return probabilities over supplied options, but a deployed agent may also need to reply in words. The present study introduces System X, a large language
- PaperSemi-supervised learning on singular data sets
We propose to model singular data clouds by subanalytic sets, and develop an approach to semi-supervised learning in this setting. It relies on a Morrey-type embedding fo
- PaperUBD-Bench: Benchmarking and Analyzing Unimodal Branch Degradation in Multimodal Perception for Autonomous Driving
Multimodal perception improves autonomous-driving performance by combining complementary sensor information. However, stronger multimodal predictions do not necessarily i
- PaperEnhanced Masked Diffusion Unlearning
Masked diffusion language models (MDLMs) generate text by iteratively unmasking tokens with bidirectional context. As these models reach real-world deployment, machine un
- PaperStepwise Reasoning Verification: Don't Generate, Classify!
Verifying the reasoning of large language models is increasingly important as they are applied to complex mathematical and scientific problems. Existing work focuses on l
- PaperDesign Considerations in Low-Resource Archival OCR: A Case Study in Lakota
Building and expanding access to digital archives supports language reclamation and creates lasting resources for community revitalization. Designing effective tools to s
- PaperA New Hope for PRNU on Modern Smartphones? Evidence That Device-Specific Fingerprints Survive Computational Photography
Photo Response Non-Uniformity (PRNU) is widely regarded as the most reliable marker for source camera identification. Recent studies, however, report high correlations be
- PaperDragonMoCap: Monocular Video-based Motion Capture for Diverse Dragon Topologies
This work explores monocular motion capture for dragon-type characters, which currently relies on manual keyframing due to the lack of high-quality datasets and parametri
- PaperRARE: Reinforcement Learning with Adaptive Rubric Evolution for Open-Ended Generation
Verifiable rewards have advanced reinforcement learning in mathematics and code. However, many valuable open-ended tasks share three properties: no automatic verifier of
- PaperMOSAIC: Multi-Objective Search for Allocating Inference Cache Across LLM Decoder Layers
The Key-Value (KV) cache is the main memory bottleneck of long-context LLM inference. Token eviction methods such as SnapKV, H2O, AdaKV and L2Norm shrink it, but they giv
- PaperPreserving the Manifold: Frozen Expert Alignment for Label-Efficient SAR Scene Understanding
Cross-modal alignment of synthetic aperture radar (SAR) imagery to natural language is constrained by two distinct failures. The first is modality mismatch: text encoders
- PaperMixture-of-Memories: Low-Overhead Language Modeling with Modular Knowledge Injection
Large language models store substantial factual knowledge in their parameters, yet this knowledge is difficult to control, update, and reliably elicit at inference time.
- PaperFrom Label Priors to Task Evidence: Efficient Long-Video Frame Selection via Bayesian GRPO
Multimodal Large Language Models (MLLMs) face significant scalability challenges in long-video understanding due to quadratic attention complexity and context window cons
- PaperUniState: Unifying Memory and Intervention for Controllable World Simulation
World models offer increasingly rich environments for exploration, yet intervening in a world while observing the consequences from freely chosen viewpoints remains chall
- PaperTowards Figurative Language Understanding in Moroccan Darija: An Evaluation of Large Language Models
Figurative language remains a major challenge for Machine Translation (MT) systems, as the intended meaning of such expressions often goes beyond literal translation. Alt
- PaperMT Forcing: Towards Stable and Consistent Multi-Turn Image Editing with Autoregressive Diffusion
Multi-turn image editing aims to modify an image according to a sequence of instructions, enabling more effective interactive visual content creation for users. However,
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.