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
- PaperSCCL-DT: Semantic-Conflict-Aware Contrastive Learning with Dual-Rule Teacher Distillation for Zero-Shot Chest X-Ray Diagnosis
Contrastive vision-language pre-training supports zero-shot chest X-ray diagnosis, but standard objectives treat every off-diagonal image-report pair in a batch as a nega
- PaperBeyond the Dominant Label: Recovering Coexisting Lesion Evidence with Multiple Instance Learning
Whole-slide images may contain coexisting lesions, yet weak supervision typically provides only the most severe diagnosis. We formulate this setting as dominant-label mul
- PaperPathology foundation models for training-free case retrieval in salivary gland tumors
In pathology, pattern recognition relies on a frame of reference built through extensive training and experience, which may still fall short when encountering rare cancer
- PaperMulti-SFT: Permissively-Licensed Multilingual Instruction-Following
Supervised fine-tuning datasets remain overwhelmingly English-centric and commercially restricted, as their content is frequently generated by proprietary models whose te
- PaperLearning Changes the World and Then What Was Learned has Changed: Training and Deploying Neural Networks in the Control Loop
Neural networks offer critical adaptability for controlling complex systems where nominal modeling proves intractable. However, when offline-trained neural networks are d
- PaperLearning from Unverified Peers via Shared Residual Distillation
A language model can generate several solutions to the same problem, some leading to correct answers and others to incorrect ones. Many post-training methods turn these t
- PaperCan AI Forecast the Extremes? Evaluating Probabilistic Weather Models on Tropical Cyclones
Weather prediction is undergoing an important shift, with data-driven AI models outperforming leading numerical weather prediction systems on average at a fraction of the
- PaperRetrofitting Recurrent Vision-Language Models from Pretrained Backbones
Recent work shows that depth recurrence can be retrofitted into pretrained language models. In this work, we adapt this paradigm for visual understanding, using depth rec
- PaperThe Right Byte First: How UTF-16 Helps Multilingual Boundary Prediction
Many hierarchical byte-level language models group bytes into patches using a learned boundary predictor whose view of the next codepoint depends on encoding and lookahea
- PaperMemory as Weights: Internalizing Long-Term History for Streaming Videos
Streaming vision-language models (VLMs) must continuously integrate information from the past while remaining responsive to current observations and user queries. Existin
- PaperWhen Reasoning Is Not Enough: Proactive Inquiry for Cross-Modal Safety in Multimodal Large Language Models
Multimodal large language models (MLLMs) can act unsafely when individually benign images and texts are interpreted jointly. Beyond implicit reasoning risk, where reasoni
- PaperBeyond Context Length: Characterising the Difficulty of Long-Context Reasoning
Long-context language models support ever longer context windows, and evaluations typically treat context length as the main indicator of difficulty. However, context len
- PaperPrism-1: Position- and Rival-Independent Scoring for System One Models
Given a state and a set of options, such as intents, tools or interface elements, System One decision models return a distribution over the options in one forward pass, w
- PaperABNAT: Attention-Based Noise-Aware Training for Robust Transformers on Analog Compute-in-Memory Systems
Transformer-based models have become the backbone of a wide range of tasks, but their intensive computation and data movement incur substantial energy overhead. Analog co
- PaperDocumenting Trofinetide Treatment Phenotypes in Rett Syndrome with a Dual-LLM Consensus Pipeline
Objective: Trofinetide, approved in 2023 as the first Rett syndrome treatment, lacks scalable real-world monitoring because chart review is labor-intensive. We developed
- PaperFAOPs: Normal Forms and an Algebra for AI Agent Workflows
Organizations increasingly encode operational procedures as multi-step agent skills, here called Agent Operating Procedures (AOPs), that must be traceable, auditable, rep
- PaperFeaTok: Feature-Loss Tokenization for Image Generation
Discrete image generators learn the distribution of tokens produced by an image tokenizer. These token representations should be easy for generators to model, not merely
- PaperProgress Reward Model for Reinforcement Learning via Large Language Models
Traditional reinforcement learning (RL) algorithms face significant limitations in handling long-term tasks with sparse rewards. Recent advancements have leveraged large
- PaperName-Bias in Large Language Models
Names carry demographic indicators such as age, gender, and race, which makes them a subtle but strong target of bias in large language models (LLMs). In this work, we pr
- PaperRethinking Successive Rejects Algorithms
In the best-arm identification problem, an algorithm adaptively selects arms to find the arm of the largest mean reward. Successive Rejects (SR) is a simple fixed-budget
- PaperMissed Detections and False Alarms in a CNN Technosignature Detector on Breakthrough Listen Data
Radio technosignature searches rely on machine learning detectors to shrink the candidate pool before a human looks at it. They are validated on held-out data from the tr
- PaperDecoding Naturalistic Speech from fMRI with Temporal Modeling and Multimodal Alignment
Reconstructing what a person perceives from their brain activity is a stringent test of whether neural recordings carry meaningful information. Naturalistic speech offers
- PaperEffectiveness of Hidden-State Probes for Localizing Reasoning Failures
Verifying the final answer of a long reasoning trace may show that the trace is wrong but it does not distinguish three cases. The problem may lie beyond the model's capa
- PaperMomentum, Commentary Tone, and Earnings Surprise in LLM Financial Forecasts
Which inputs drive a language model's financial forecast? We construct synthetic earnings announcements that independently reverse 20-day momentum, non-informational comm
- PaperWEAVE: Weaving Real-World Code Evolution into Dependency-Structured Tasks for Benchmarking and Training Code Agents
Real-world software engineering rarely consists of isolated changes. Features, migrations, and systematic fixes often unfold across multiple pull requests (PRs), requirin
- PaperETH: Data-Balanced Heterogeneous Pipeline Parallelism for Training Large Models
Current heterogeneity-aware training systems for large models balance workloads by assigning unequal numbers of layers across pipeline stages, a strategy aimed at equaliz
- PaperDesigning Experiments for External Decision Makers
Standard Bayesian experimental design (BED) methods assume the experimenter alone will act on the data, choosing the best action given their own beliefs and goals. In pra
- PaperGraphACM: Graph-based Action Consistency Measurement for Uncertainty Quantification in LLM Agents
Behavioral consistency across repeated executions provides an informative signal for assessing the reliability of large language model (LLM) agents. However, existing app
- PaperSelection Is Not Learning: Choosing Model Futures
Self-evolving language models train on tasks they generate, so every round must decide which updated model the next round inherits. Current loops such as R-Zero, Agent0,
- PaperAugment the Cache, Replace the Activation: A 2x2 Study of Internal-State Sharing
Multi-agent systems built from frozen language models communicate through text, which discards the internal state the sender already computed and makes the receiver pay t
- PaperNot All Unlabeled Data Are Equal: Unlabeled Data Selection for Semi-Supervised QSAR Modeling with Large Chemical Repositories
Semi-supervised learning (SSL) is particularly attractive in domains where labels are expensive to obtain, while unlabeled examples are readily available. Quantitative St
- PaperDemoStream: Batched Task-and-Motion-Plan Optimization for Automated Learning from Demonstration
Learning from demonstration is an effective strategy for endowing robots with manipulation capabilities but requires training on datasets comprised of massive amounts of
- PaperPriming Base Models for Agentic Post-Training: An Open Midtraining Recipe
Frontier models, general-purpose and domain-specific alike, now include a midtraining stage between pretraining and post-training, but little has been published about how
- PaperWhen Models Misread Ink: Auditing VLMs for Arabic Calligraphy Recognition
Arabic calligraphy is a high-stakes cultural visual domain for Muslim communities, yet VLM evaluations rarely test its fine-grained script traditions. We audit 12 VLMs on
- PaperCARA: Causally Guided Retrieval Agent for Question Answering
Retrieval-augmented generation over text-rich knowledge graphs requires identifying evidence that contributes to answering a question, rather than merely matching its tex
- PaperClose Enough is Nowhere Near: Fidelity-Consumability Decoupling in KV Caches
Multi-agent LLM systems communicate in text, which is lossy and wasteful: the sender throws away the reading it already did. A growing literature instead transmits the KV
- PaperGraphBEAT: Graph-based Bucketized Event Aggregation Over Time for Early Risk Stratification of Gastrointestinal Cancers
Longitudinal electronic health records (EHRs) contain complementary diagnostic and laboratory information about patient health. However, irregularity, sparsity, heterogen
- PaperVisual Sanad: Auditing Vision-Language Models for False Acceptance of Qur'anic Citations
Vision-language models (VLMs) are increasingly used to interpret religious, educational, and culturally sensitive visual content, yet their reliability on citation verifi
- PaperStateful Testing for Deep Learning Compilers
Modern deep learning compilers compile models lazily and cache artifacts across invocations. Retained compiler state can make a later invocation incorrect even when it is
- PaperInterfaces and Modules: A Scalable Representation for Weight-Space Learning across Architectures
Weight-space learning across architectures requires representations that respect parameter symmetries and scale to large networks. Existing equivariant tensor encoders re
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.