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…
Friday 16 October
- PaperFrom SEC Filings to Financial Signals: Evaluating LLMs on Stock Market Reactions and Analyst Forecasts
Form 10-Q MD&A sections combine long-form management narrative with accounting and forward-looking information. Benchmarks for financial filings commonly evaluate questio
- PaperCan Compact Open-Weight Large Language Models Recover Mobility Events from Incomplete Trajectories? A Controlled Evaluation Using Air Trips
Incomplete mobility trajectories can obscure the observations needed to identify important travel events and their endpoints. This study evaluates whether compact, locall
- PaperDesirability Confirmation: Relational Sycophancy in AI Intimate Roleplay
Research on LLM sycophancy has largely focused on propositional agreement, in which models echo users' beliefs, preferences, or judgments. Adult intimate roleplay present
- PaperAM-Bench: A Unified Taxonomy and Evaluation Suite for Agentic Misalignment
As LLM-based agents are deployed with increasing autonomy in real-world environments, a critical failure mode emerges: agentic misalignment, where agents choose harmful a
- PaperBest of Both Worlds: Fine-Tuned Small Models Complement LLMs for Cost and Performance Benefits
BERT-based models require thousands of labeled samples to train. Larger models like GPT-X require only 1-5 examples per class. However, performance, cost and time tradeof
- PaperSLA-LENS: From Classroom Transcripts to CSLA-Informed and Evidence-Linked L2 Interaction Analytics
What happens after a learner makes an error, and how does the instructor's response shape the next turn? Investigating these exchanges across classrooms requires context-
- PaperDynamic Neural Optimal Transport for Subset Alignment
We study optimal transport between distributions when only a subset of the target population is relevant to the source. The goal is to map the source distribution to a re
- PaperCortex: A Fixed-Point Theory of Governed Coding Agents - Technical Report
A coding agent combines a large language model (LLM) with a harness that plans, edits, and executes code. We study Cortex, a supervisory layer for pre-execution governanc
- PaperMOSS: A Production Framework for Monitoring and Diagnosing Semantic Failures in Search and Recommendation Systems
Detecting semantic failures in production recommendation and search systems is hard: behavioral metrics lag by days, manual review does not scale, and most LLM evaluation
- PaperCan This LLM Annotate My Data? Estimating Zero-Shot LLM Performance
Large language models (LLMs) are increasingly used in annotation tasks with varying success. While several studies have demonstrated the opportunities and shortcomings of
- PaperProbing Ambiguity: Adversarial Intent Resolution for Robust Text-to-SQL
Text-to-SQL systems typically assume a one-to-one mapping between natural-language queries and correct SQL translations. In practice, however, many queries are inherently
- PaperCoCoNet: Convex Conformal Network for Multi-Dimensional Uncertainty Regions
Conformal prediction (CP) provides distribution-free coverage guarantees under exchangeability, but the efficiency of its prediction regions depends critically on the cho
- PaperTowards Reinforcement Learning for Space Robotics: Fast Training and Reliable Real-World Transfer
This work demonstrates the use of a fast simulation-based training framework to learn control policies using reinforcement learning. The hardware requirements are minimal
- PaperExtending Myerson's Optimal Auctions to Correlated Bidders via Neural Network Interpolation
We aim to design revenue-maximizing single-item auctions that are deterministic, strategy-proof, and ex post individually rational --- the quintessential fundamental mode
- PaperEncoder-Free Multimodal LLMs Learn Implicit Encoders
We empirically analyze two recently proposed encoder-free multimodal LLMs, Gemma-4 12B and Inkling-Small. Unlike previous multimodal LLMs, these models do not use modalit
- PaperGhost Attack: Using 19th-Century Illusions to Fool 21st-Century Biometrics
While the Pepper's Ghost illusion is a 19th-century optical technique, we found that this forgotten gimmick exposes vulnerabilities in modern face recognition systems. Th
- PaperPreserving Reasoning Diversity in Reinforcement Learning with Verifiable Rewards via Adaptive Replay
Reinforcement Learning with Verifiable Rewards (RLVR) improves the reasoning capabilities of large language models, but often reduces the diversity of their reasoning beh
- PaperWho Plans, Who Edits? Verified, Cost-Aware Division of Labor for LLM-Driven Analog Layout Repair
Language-model agents can repair analog layouts when sign-off tools check every edit, but which model should plan a repair, which should edit it, and at what cost remain
- PaperCensored Flow Matching for Synthetic Time-to-Event Generation
Generating time-to-event data is increasingly important in survival analysis, but it remains statistically challenging because event times are often censored and thus pre
- PaperAnalyzing Repetition and Interference Effects in Memory-Constrained User Simulators
User simulators can help evaluate and train AI systems to interact with humans at scale. To do so, evaluation of user simulators must measure behavioral parity with peopl
- PaperLoopHIL: Looping Hardware into LLM-assisted Agents for Wireless Embedded Systems
LLM agents are widely used for software development and debugging, but their adoption in embedded systems, especially for wireless tasks, remains limited. This is because
- PaperTraining-Free Prompt Selection for Efficient Reinforcement Learning With Partial Rollouts
Reinforcement learning with verifiable rewards (RLVR) has emerged as a prominent paradigm for training reasoning models, but its computational cost makes efficient data s
- PaperLanguage Models are Lazy Poets: Creative Mode Collapse at Scale
While aligned large language models (LLMs) can successfully complete many creative tasks, their outputs tend to be highly self-similar. Though solutions to this problem o
- PaperHidden Trajectories Don't Lie: Correcting Corruption Drift for Test-Time Adaptation
Test-time adaptation (TTA) adapts pretrained models to distribution shifts encountered during deployment. However, most existing methods rely on the weight representation
- PaperLandmark-Free and Scale-Blind Multi-View Registration of Preoperative Liver Models to Intraoperative Surfaces
Augmented-reality guidance in laparoscopic liver resection requires aligning preoperative 3D liver models from CT/MRI with intraoperative surfaces. Monocular reconstructi
- PaperSWE-Bench Pro V2: A Cleaner, Harder-to-Game Coding Benchmark
SWE-Bench Pro is a widely used benchmark of long-horizon software engineering tasks for coding agents. As agents improve, they reach task issues earlier agents never touc
- PaperPREEMPT: Proactive Robustness Evaluation under Editing for Media Protection Techniques
Proactive image protection methods aim to defend visual content against unauthorized manipulation and generative misuse by embedding protective signals into images before
- PaperCertified neural approximations for parabolic obstacle problems
Residual-trained neural surrogates carry no error guarantee, a limitation for free-boundary problems such as phase change and contact. We derive guaranteed error bounds f
- PaperCandidate-dependent residual routing trades top-of-list accuracy for recall in sequential recommendation
Candidate-dependent routing lets a sequential recommender weight a user's past behaviors differently for each item it scores. We test whether this flexibility helps by ad
- PaperDistillation, Self-Training, and the Fragility of Learned Chemical Reasoning
Automating synthesis planning for small-molecule drug design requires chemical reasoners that are accurate as well as open to inspection and adaptation, yet frontier lang
- PaperTowards an Intelligent Decision Engine for Smart Contract Deployment
Layer 2 (L2) blockchain solutions emerged in recent years, predominantly in the Ethereum ecosystem, as a viable option for scaling a main blockchain network (L1). However
- PaperAgents' Last Doubt: Knowing When to Act and When to Step Back in Tool-Using Agents
Tool-using LLM agents repeatedly face decision points under uncertainty, choosing between autonomous action, additional information gathering, and human escalation. These
- PaperOn Reparameterizing the Score Function
Policy gradients for autoregressive sequence models differentiate each token's log-probability while holding the conditioning history fixed. This discards information abo
- PaperReasoning with Context Management and External Memory
Reasoning models maintain information about the status of their reasoning process through in-context memory. Complex problems require larger context windows and memory re
- PaperBootstrap Stochastic Interpolant Tree for Inference-time Search Under Sparse Reward
Tree-based samplers offer a compelling alternative for scalable inference-time search, bypassing the per-step reward and gradient dependencies that introduce systematic b
- PaperMulti-author style detection with stylistic embeddings
We investigate the use of Large Language Models (LLMs) in multi-author style change detection. Using off-the-shelf LLMs or supervised fine-tuning solely within the target
- PaperPrecision Cotton Disease Management: Leveraging UAV Imagery and Custom YOLO Deep Learning Framework for Enhanced Detection
Cotton sustains the textile economies of over 80 countries with an annual yield of 113 million bales, yet 30-60% of yield losses are still attributed to viral, bacterial,
- PaperLarge language model and reinforcement learning based autonomous construction and progress updates
Due to the rapid growth of the global population, traditional construction methods are gradually unable to meet the current housing demand. The advancement of machine lea
- PaperSelf-Improving Video-to-Action Models
Video generative models are an emerging tool for embodied agents: they can serve as scalable visual planners, generating videos that depict how to complete previously uns
- PaperSERO: Semantic Prediction for Single-Step Object Removal
Object removal and semantic inpainting of missing regions remain inherently ill-posed, as multiple plausible completions may exist for a given scene. Recent diffusion-bas
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.