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…
Tuesday 20 October
- PaperMemory as Code: Declarative Retrieval over Codified Long-Term Memory
In long-term memory systems, memories are constructed from interaction histories and retrieved in response to queries, enhancing the reasoning ability of LLM agents. In c
- PaperE8-QAT: Efficient 2-Bit Quantization-Aware Training with Implicit Lattice Codebooks
Low-bit quantization reduces the memory footprint of large language models, but preserving accuracy with efficient training remains challenging. Scalar quantization encod
- PaperVLA-Retain: Benchmarking Cross-Dimension Effects of Vision Tuning in VLAs
Vision-language-action (VLA) models transfer knowledge from large-scale pretraining into robot control, but their manipulation performance remains sensitive to changes in
- PaperPanoGraphGS: Unifying Panoptic Segmentation and Hierarchical 3D Scene Graphs with Gaussian Splatting
3D scene graphs support language-guided navigation by organizing physical entities and their containment and spatial relations into hierarchical maps. Building such struc
- PaperA Principled Optimal Transport Framework for Frame Selection in Long Video Understanding
Long-video understanding with multimodal LLMs is fundamentally constrained by the mismatch between video length and the model's limited visual context budget, making fram
- PaperEASformer: Environment-Action-State Alignment for Industrial Generative Ranking
Modern industrial ranking systems increasingly adopt generative recommendation (GR) paradigms, in which user behavior sequences and non-sequential (NS) features are token
- PaperNeoWorld-3: From Pixels to Code-Defined Physical Worlds
Simulation-ready world reconstruction demands physical interactivity beyond visual realism, which existing black-box 3D generation fails to deliver. We present NeoWorld-3
- PaperInfluence Is the Target-Response Jacobian Times Residuals
We introduce the target-response Jacobian $J = [\partial \hat y_i/\partial y_j]$, which measures how model predictions respond to changes in individual training targets.
- PaperPattern Intelligence: Unsupervised, LLM-Interpreted Discovery of Systematic Underpayment and Denial Patterns in Healthcare Revenue Cycle Management
Healthcare providers lose substantial revenue to systematic payer underpayments and claim denials, yet identifying the recurring, correctable patterns behind them remains
- PaperTemporal Evidence Allocation For Longitudinal Clinical Retrieval: A Position And Technical Report
Electronic health records are written to support care, not retrieval. Across years of oncology notes, the primary diagnosis is restated in report after report, while the
- PaperPhonoBridge: Error-Aware Phoneme-Mediated EMG-to-Text Reconstruction
Electromyography (EMG) provides a non-invasive means of decoding silently articulated speech into text, but accurate decoding remains challenging due to limited availabil
- PaperCovNav: Conformal Prediction-Guided Adaptive Inference for Object Goal Navigation
In object goal navigation (ObjectNav), an embodied agent must find a target object (e.g., "find a bed") in a previously unseen environment, relying on spatial commonsense
- PaperCyberHull: Deterministic Malicious URL Isolation via Convex Hull
The emergence of increasingly sophisticated and evasion-resistant phishing attack strategies represents a significant threat to modern cybersecurity, particularly in cybe
- PaperHybrid Momentum Methods for Optimizing Deep Learning Models
Momentum is central to stochastic optimization in deep learning, including the training of large language models. Classical momentum methods typically rely on a fast expo
- PaperReusing Assurance Evidence in AI Pipelines: Validity Conditions, a Fail-Closed Release Gate, and a Replay of 714 Public Data Version Control Pipelines
Rerunning every governance control after every change to an artificial intelligence (AI) pipeline is expensive, so teams reuse earlier results. Reuse is safe only if each
- PaperNeural Operator Splitting for Fluid Dynamics in Complex Geometry
Solving dynamical systems in complex and diverse geometries remains challenging for both numerical solvers and learning-based surrogate models. We propose Neural Operator
- PaperReusing Multimodal Agents: Efficient Evaluation of Sound Designs in Games
This paper introduces a novel framework for efficiently evaluating in-game sound designs using multimodal learning and reinforcement learning. Sound design significantly
- PaperPairwise Learning Increases Data Efficiency in Deep Neural Networks
Deep neural networks often fail at small-sample regression, collapsing to low-variance predictions that miss individual differences. Here, we introduce a pairwise compari
- PaperInferring continuous cognitive traits from limited neuroimaging data using pairwise convolutional neural networks
Individual differences in cognitive abilities vary widely, yet the structural brain features supporting these differences remain poorly understood. Traditional brain-beha
- PaperWhen Can LLM Reasoning Reliably Reuse Intermediate Results?
Sampling complete solutions gives large language models more chances to solve a problem, but each attempt starts again. For tasks with several subproblems, all required a
- PaperPLaCA: Learning Patch-Level Future Latent Change for Action Generation
Vision-Language-Action (VLA) models generate robot actions from visual observations and language instructions, but effective manipulation also requires anticipating how t
- PaperPACE-MoE: Adaptive Domain Sampling and Domain-Specific LoRA for Medical Visual Grounding
Medical visual grounding requires models to align clinical descriptions with spatial evidence across heterogeneous imaging domains. However, existing multi-domain post-tr
- PaperDoes Multi-Agent Collaboration Pay When Agents Serve Users? Testing Agent Scaling in Dual-Control Settings
Multi-agent systems (MAS) built from language models are deployed on the premise that collaboration beats a single-agent system (SAS), yet when it pays is unclear. The mo
- PaperA Unified Attack Framework against Statistical Generative Watermarks for Large Language Models
Watermarking has emerged as a key tool for identifying text generated by large language models (LLMs), with current schemes embedding statistical signals into the generat
- PaperCorpus Quality Improves, Retrieval Utility Does Not: An Ablation of Preprocessing and Refinement in a Speech-to-QA Pipeline
Practitioners building training corpora with a pipeline of language models keep a preprocessing or refinement (post-process) stage when switching it on raises the corpus
- PaperSpeak vs. Know: Balancing Behavior and Knowledge Distributions of Large Language Models
Recent work reports that the distribution verbalized directly in the output text aligns far better with human opinion distributions than the next-token log-probability di
- PaperCUA-Recovery: Benchmarking Error Recovery in Long-Horizon Computer-Use Agents
As computer-use agents (CUAs) move to long-horizon workflows spanning multiple applications, undetected errors can silently corrupt persistent state and cause cascading f
- PaperBCT: Bayes-Consistent Tempering for Flow Language Models
Temperature scaling is typically applied as a post-hoc transformation of model probabilities. In posterior-induced flow language models, this creates two mismatches. Firs
- PaperEnsemble-Aware Structural Encoding (EASE): Conditioning Protein Encoders on Peptide Conformational Ensembles
Protein foundation models provide transferable representations for downstream peptide prediction tasks. However, existing representations typically reduce a peptide to a
- PaperSCODEL: Shared Canonical Ontology Definitions for Food Entity Linking and Ontology-Grounded Recipe Knowledge Graphs
Identifying recipe entities and linking them to ontology concepts is fundamental for semantic recipe understanding. However, food mentions in recipes are often ambiguous,
- PaperWhen Does Feedback Help? Auditing Learned Voltage-Clamp Experimental Design
A learned scientific controller can outperform a misspecified planner without benefiting from feedback. We audit two synthetic voltage-clamp tasks with a training-selecte
- PaperA Two-Way Street: Surveying the Interplay between Code-Mixing and Native Languages in Text and Speech
Systems for code-mixed (CM) text and speech rarely start from scratch. CM data is scarce, so most work borrows from the languages being mixed, which we call native langua
- PaperPAR: Progress-Aligned Recurrence for Length Generalization in State Tracking
Looped language models can run more iterations at test time, but additional iterations need not help them solve longer problems. For sequential state tracking, final-answ
- PaperTriGeoBench: A Multimodal Mathematical Geometry Benchmark with Figures and TikZ
Multimodal Large Language Models show strong vision-language capabilities, yet their geometry-centric reasoning remains insufficiently understood. Existing mathematical b
- PaperFrom Outcomes to Steps: Reliable Success-Aware Critic Learning for Long-Horizon Language Agents
Reinforcement learning for long-horizon language agents requires identifying whether intermediate actions make eventual task success more or less likely when supervision
- PaperA Head Camera Is (Almost) All You Need: An Electronics-Free UMI Glove Labelled and Observed by One Moving Camera
Handheld demonstration devices decouple data collection from the robot, but conventional designs burden the hand with a wrist camera, cables and a pose tracker (SLAM, an
- PaperA Radiation-Hardened, Fault-Aware Quantized Neural Network That Self-Heals
Deep learning (DL) models are increasingly being deployed into radiation-challenging environments in spacecraft, particle accelerators, and, soon, space-based data center
- PaperLocal Allow, Global Deny: Why Per-Action Authorization Does Not Compose in LLM Agents
Autonomous LLM agents act through tools under per-action authorization: a local guard screens each tool call in isolation. We show that local authorization does not compo
- PaperProvisioning Robust and Efficient LiDAR Perception for Autonomous Driving
LiDAR-based 3D object detection is a core perception service for autonomous driving, but deployment requires robustness to point-cloud corruption while meeting latency an
- PaperLearning Inter-Graph Interactions Between Heterogeneous Substructures of Chemical Systems
Complex chemical systems containing heterogeneous substructures are common in real-world applications. Various physical phenomena of the complex chemical systems are deri
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.