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
- PaperThink Before You Transcribe: Context-Steered Reasoning for Hotword-Aware Speech Recognition
Contextual automatic speech recognition (ASR) improves rare-entity recognition by supplying candidate hotwords, but retrieved candidates may be incomplete or incorrect. A
- PaperAirMPA: A Meteorology-to-Pollution Adapter for Global Air Quality Forecasting
Accurate real-time forecasting of atmospheric pollutants is essential for reducing exposure risks and improving public health. Traditional numerical forecasting systems s
- PaperFair Regression under Approximate Demographic Parity
Exact demographic parity requires the same prediction distribution across sensitive groups. In regression, this can be too restrictive and reduce predictive accuracy. We
- PaperSAR: Learning Global Item-Space Matching and Geometry-Aware Placement Ranking for Buffered Online 3D Bin Packing
Online 3D bin packing with a bounded buffer requires irreversible item-selection and placement decisions under limited knowledge of future arrivals. Feasibility alone is
- PaperCoMem: Learning to Anticipate Failures from Retrieved Experience
Reflection lets LLM agents improve from their own attempts, but the memory it builds is local to a single task, so an agent reflecting on its own tends to revisit the sam
- PaperCan LLM User-Proxies Stand In for Humans in Reliance Measurement? Replicating Rel-A.I. with Simulated Users
Can language-model user proxies reproduce human reliance on an AI answer across contexts? Published simulated-user studies do not establish validity for this partial-answ
- PaperUniJev: Separating Accuracy from Calibration in Trimodal System One Decision Models
System One models produce probabilistic judgments that software can consume directly, making reliable confidence as important as answer accuracy. Yet joint training acros
- PaperSee the Future, Classify the Present: Stochastic Latent World Modeling for Hyperspectral Images
Hyperspectral image classification (HSIC) relies on static spatial-spectral representations learned from labeled samples, limiting its ability to model structured depende
- PaperDetection Augmented Learning In Non-Stationary Bandit Environments
We study the problem of non-stationary bandits without knowledge of the environmental changes. We propose Detection Augmented Learning (DAL) a black-box paradigm that com
- PaperOpenSaC: A Python Library for Search as Code in Deep Research Agents
Deep research agents investigate complex questions through iterative search, source examination, and evidence synthesis. A conventional workflow alternates reasoning with
- PaperStanding on the Shoulders of Giants: Enhancing LLM Agents for Automated Fact-Checking with Human Expert Skills
Automated fact-checking (AFC) systems powered by large language model (LLM) agents still face challenges in evidence retrieval and claim verification. Existing approaches
- PaperFrom Trace to Fix: Residual Task State in Long-Horizon Agents
Recovering from failures in long-horizon, stateful language agents is challenging because the action introducing a defect, the symptom exposing it, and the persistent sta
- PaperVHA: VQA-based Hallucination Assessment for Generative Image Super-Resolution
Generative image super-resolution produces visually realistic high-resolution images, but may also introduce hallucinations by adding unsupported content or altering exis
- PaperTruncated Reasoning Under a Budget: Evaluating System-1 Models as Decision-makers
Large language models (LLMs) often generate more reasoning tokens than needed. Limiting the reasoning budget reduces cost, but forcing an answer from an incomplete trace
- PaperEvalRx: Agentic Diagnosis and Verified Repair of Foundation Models
Model evaluation reveals where models fail, but rarely why or whether a proposed fix genuinely works. We introduce EvalRx, an open-source agentic framework for statistica
- PaperTRACE: Tracking Multimodal Clinical Trajectories for Inpatient Risk Prediction
Accurate inpatient risk prediction requires modeling heterogeneous clinical evidence that accumulates irregularly over time. This challenge spans in-hospital mortality, p
- PaperActTime: Action-Conditioned World Modeling for Time Series
Time-series models increasingly condition on known future inputs. In controlled systems, some of these inputs are actions that can be changed, compared, and optimized bef
- PaperComputation, Not Memory: Chain-of-Thought and State Tracking in LLM Agents
Language-model agents often reason before they act, and the value of monitoring that reasoning depends on how it relates to their actions. We ask how an agent's actions d
- PaperRemember Less, Adapt Longer: Bounded-State In-Context Reinforcement Learning with Recurrent Summary Memory
In-context reinforcement learning (ICRL) enables agents to adapt to new tasks without parameter updates, relying on memory to retain what they learn from experience. For
- PaperWhich Answers Agree? Evaluating Self-Consistency from Incomplete Logs
Self-consistency answers a question by generating multiple responses and selecting the most frequent answer. Its evaluation requires both correctness labels and informati
- PaperNADS: Navigator-Guided Data Selection for Mitigating Catastrophic Forgetting in Fine-Tuning
Catastrophic forgetting is a central obstacle in single-stage fine-tuning of large language models (LLMs) on a new task, especially when the original pretraining data are
- PaperCognitively Decoupled Meta-Induction for Out-of-Distribution Generalization
In-context learning (ICL) tackles downstream tasks conditioned on demonstrations. This paradigm relies heavily on neighbor-based matching between queries and demonstratio
- PaperMAPS: A Multi-Agent Personalized Script-Driven Video Advertising System Enhanced by Reinforcement Learning
With the rapid growth of online video consumption, video advertising has become a dominant component of digital advertising. Most personalized video advertising systems f
- PaperBayesian Model Discovery with Language Models: Closing the Loop between Hypotheses and Experiments
Scientific model discovery requires proposing candidate models of an unknown system and designing experiments that discriminate among them. However, LLM-based approaches
- PaperFundamental Limits of Information-Theoretic Secure Aggregation with User Dropouts in Federated Learning
Secure aggregation enables a server to compute the sum of users' gradients or model updates without revealing individual values. With user dropouts, correlated random key
- 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
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.