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
- PaperKEEP-Bench: Evaluating Evidence Preservation in Context Compression
Context compression improves long-context efficiency but may introduce faithfulness issues through an information bottleneck. Existing evaluations rely on QA metrics, but
- PaperRefCraft: Benchmarking Visual-Reference-Conditioned Agentic Generation through Web Development
Beyond basic tool use and coding skills, effectively incorporating visual references into agentic generation is equally essential for applying AI agents to real-world pro
- PaperMemT-1.0: Towards Memory-Native Evolution
Memory-native evolution requires making memory an intrinsic capability of foundation models, enabling them to continuously accumulate and utilize information. To this end
- PaperSpecMRL: Redesign Matryoshka Representation Learning within Parametric Spectrum
Matryoshka Representation Learning (MRL) is designed to support flexible representation sizes by jointly optimizing nested prefixes. While effective, this design lacks an
- PaperAfriBED: a Speech Recognition Bias Evaluation Dataset for Low Resource African Languages
Despite advancements in automatic speech recognition systems (ASR), current systems exhibit speaker-attribute bias, i.e., their speech recognition performance is biased a
- PaperOpen-Form Geometric Style Transfer
A geometric style learned from one family of shapes is typically applied to new shapes from the same family. We consider a more challenging setting: learning the geometri
- PaperASTOR: Benchmarking and Improving Autoformulation for Soft-Constraint Optimization with a Formal Grammar
Real-world decision problems combine two qualitatively different kinds of constraints: requirements that must be satisfied, called hard constraints, and preferences that
- PaperReuF2F: Benchmarking Coding Agents on Formalized Undergraduate Research Problems
As AI systems begin to resolve open research problems, reliable verification becomes increasingly important. Formal mathematics provides a trusted framework for mathemati
- PaperNext Best Action: Causal Constrained Offline RL for Business Action Targeting
Next Best Action (NBA) systems must select among customer interventions (e.g., discounts, promotions, and lifecycle actions), maximize long-term economic value, satisfy c
- PaperReal-Time Radar Semantic and Panoptic Scene Understanding
Robust scene understanding under varying environmental conditions is essential for safe autonomous driving. While cameras and LiDAR degrade in adverse weather and poor li
- PaperPICA-WAM: Visual Perturbation Invariance via Cross-Appearance Self-Alignment in World Action Models
World Action Models (WAMs) jointly predict future video and generate actions, yet remain sensitive to task-irrelevant visual perturbations, i.e., changes in visual appear
- PaperState World Models: Execute the Rules, Generate the Pixels
Existing world models can generate action-conditioned video from a single image. Many focus on camera movement, allowing users to explore the generated scene. However, na
- PaperPhysical AI: Concepts, Techniques, and Challenges
In recent years, physical artificial intelligence (physical AI) has experienced rapid development, capturing significant attention in academia and industry. However, the
- PaperSafety Mid-Training: Internalizing LLM Safety as a Foundational Capability
Safety alignment for large language models (LLMs) is primarily performed during post-training, while recent work has also begun incorporating safety data into pre-trainin
- PaperWhat Language Adds, and at What Cost: Four Controlled Probes of Pathology Vision-Language Models
Vision--language models (VLMs) promise to make computational pathology queryable and able to draft reports, but how much language adds beyond the vision backbone is uncle
- PaperScaling Parameter-Efficient Fine-Tuning for Brain Encoding
Brain encoding models aim to predict neural responses to stimuli. The most widely used approach fits readouts from frozen pretrained backbones. Using neural data to train
- PaperMise-en-Video: Fine-Grained 3D Control for Multi-Shot Video Generation
Recent advances in text-to-video generation have enabled high-fidelity single-shot synthesis, yet practical storytelling creation requires multi-shot videos with both str
- PaperLearning to Refer: Inference-Time Collaboration in Decentralized Federated Learning
In decentralized federated learning, heterogeneous clients may develop complementary expertise, yet each query is typically evaluated only by the client where it arrives.
- PaperTeacher Supervision, Fixed Representations and Calibration: Exact Risk Calculations for Candidate-Scoring Decision Models
Candidate-scoring decision models return a probability distribution over a presented set of answers. Public documentation of one such system, Jev, and of an open counterp
- PaperCross-Lingual Reusability of LLM Pipelines: Financial Extraction, Multilingual Reasoning, and Semantic Screening
Financial institutions increasingly deploy large language models (LLMs) in multilingual markets, raising a practical question: can pipelines developed and validated in En
- PaperTwo hidden layer suffice: the caterpillar net
Every continuous piecewise linear (CPWL) function is a finite signed sum of maxima of affine functions, making maximum representation a central problem in the study of th
- PaperOn Data Scaling in Tabular ML: More Data, Better Generalization?
Recent work in tabular machine learning has emphasized the importance of diverse and realistic evaluation settings. The niche of large-scale (1M+) data, however, remains
- PaperSOMA: Continuous Monitoring and Intervention for System Two Reasoning with System One Models
Reasoning models often run into problems without noticing them, even when symptoms are visible in their own text. In humans, metacognition separates monitoring from contr
- PaperTraining with ML-labeled Data via Stochastic First- and Zeroth-Order Optimization
Training a machine learning (ML) model is an optimization process that typically requires a set of examples with ground-truth labels beforehand. Obtaining these ground tr
- PaperCooperative Multi-Agent Reinforcement Learning for Market Making on Prediction-Market Order Books
A market maker provides liquidity by quoting prices to buy and sell an asset, earning the spread while managing inventory risk. We study market makers trained with multi-
- PaperLG-Bench: A Graph-Structured Evaluation Benchmark for Life Sciences
Traditional evaluation benchmarks reduce inherently interconnected scientific knowledge in life sciences into flat lists of questions, disregarding the underlying topolog
- PaperRESIN: Multi-Chain Reasoning with Entity-Structured Indexing
Multi-chain reasoning is a challenging task not only because the multi-chain evidence is dispersed, but also because different parts of reasoning may require distinct, in
- PaperGame of Phones: Harnessing Game Theory and LLMs in 'Bot Wars' to Counteract Phone Scams
Phone scams impose substantial and growing costs on individuals and financial systems worldwide, yet existing countermeasures impose no resource cost on perpetrators. Str
- PaperV-JEPA Hand: Simple, Accurate and Fast 3D Hand and Camera Trajectory Recovery from Egocentric Videos
Egocentric video supports diverse applications, including robot learning, augmented reality, and human activity understanding. Recovering metric 3D hand trajectories from
- PaperRobustness of Internal Signals for Hallucination Detection in Vision-Language Models
When given an image and a text prompt, vision-language models (VLMs) can produce seemingly sophisticated text responses. However, they are also prone to hallucinate objec
- PaperTopological Sheaves of Irreducibility: A Theoretical Framework for Multi-Agent Task Obstructions
Multi-agent systems can differ under identical agents and communication budgets when they support different forms of joint interaction. We introduce Topological Sheaves o
- PaperMonsoon: Scalable Spontaneous Speech Collection for Low-Resource ASR in 50 Languages
For most languages, automatic speech recognition (ASR) is limited less by model architecture than by a lack of accurately transcribed spontaneous speech. We present Monso
- PaperHarnessPro: Recursive Harness Self-Improvement with Pareto Optimization for Performance-Cost Trade-offs
Harness development plays a crucial role in building capable AI agents. Recent approaches improve harnesses through recursive self-improvement (RSI), but their performanc
- PaperChannel-Level Mask Guidance for Slimmable Image Compression
Learned image compression (LIC) has achieved promising rate-distortion performance, but most methods lack scalability for diverse platforms with varying computational and
- PaperSimulation Priors for Rapid Adaptation in Model-Based RL for Autonomous Racing
Reinforcement learning enables learning high-performance control policies, but its reliance on extensive interaction limits deployment on physical systems where data coll
- PaperTokenGate: Adapting LLMs for Fast and Memory-Efficient Prefill with Learned Token Pruning
Expert human readers process large inputs (e.g., code repositories and long documents) by skimming to closely read only what matters. On the other hand, language models p
- PaperBeyond Omni: A Unified MLLM for Embodied Sensory Understanding
Recent embodied systems increasingly build on multimodal large language models (MLLMs) for their pretrained understanding and reasoning capabilities, but their perception
- PaperTrajectory Replay: Continuous-Time Mixture Transport for Lifelong Generative Models
Adapting pre-trained continuous-time generative models to sequentially incoming data without forgetting earlier tasks is a central challenge in lifelong learning. A leadi
- PaperGradient descent reaches arbitrary accuracy in a fixed number of large steps on multiclass logistic regression
We show that gradient descent (GD) with step size $η$ can achieve $\varepsilon$ optimality gap on the multiclass logistic regression loss in a number of iterations $T$ th
- PaperrecAMPLIFY: Large-Scale Pretraining of Recursive Protein Language Models
Protein language models (pLMs) are powerful tools for protein annotation and mutation-effect prediction, but progress has largely depended on scaling model size and data,
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.