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
- PaperNot All Test-Time Compute Is Evidence: Model-Specific Bias in LLM Reasoning
Test-time scaling methods implicitly assume that additional computation from the same model provides independent evidence. We show that this assumption fails within a sin
- PaperMAS-Bai: Linguistically Informed Adaptive Multi-Agent Translation for Bowen-Script Bai
Large Language Models (LLMs) remain unreliable for extremely low-resource languages whose writing systems conflict with high-resource pretraining priors. We study Bai-Chi
- PaperNon-Parametric Optimization for Scalable Learning in Stochastic Decision Problems
Stochastic optimization (SO) plays a central role in decision-making under uncertainty. Among SO problems, time-varying stochastic optimization (TV-SO) is particularly im
- PaperValidating LLM-generated political networks with survey-reported partisan exposure
Large language models (LLMs) are increasingly used to simulate human behavior in social science research, including decisions, interactions, and social relationships. How
- PaperFraming Spatial Hearing within the Free Energy Principle: A Hierarchical Model of Perceptual Learning
Spatial hearing relies on dynamic internal representations to decode spatial information from ever-changing acoustic conditions. A fundamental example is sound localisati
- PaperFuzzInsight: Navigating the Efficiency-Effectiveness Trade-off in Coverage-Guided DNN Fuzzing
Collecting and labeling diverse test datasets for evaluating Deep Neural Networks (DNNs) is costly and time-consuming. This has motivated coverage-guided fuzzing techniqu
- PaperOfficeTown: Generative Organizations for Evolving Agent Intelligence
AI agents increasingly use files and software tools to produce professional deliverables. Such work draws on materials, decisions, and feedback accumulated across assignm
- PaperProportionality in Ranking Compression
Motivated by applications in reinforcement learning from human feedback, we consider a setting where a given collection of rankings needs to be compressed into a smaller
- PaperVisual Causal-chain Bookmarking: Retrieval-Weighted Credit Assignment for Reinforcement Learning from Delayed Reward
RL agents trained on a single trajectory-level return face a credit-assignment problem: when a reward arrives many steps after the decision that caused it, every action g
- PaperLangNCO: Compiling Natural-Language Constraints into Inference-Time Interventions for Neural Combinatorial Optimization
Neural combinatorial optimization (NCO) rapidly produces high-quality solutions for problem structures encountered during training, but operational requirements may chang
- PaperA Stronger Teacher Within: Strengthening MoE Models via On-Policy Bidirectional Distillation
Reinforcement Learning with Verifiable Rewards (RLVR) has substantially improved Mixture-of-Experts (MoE) LLMs, but its outcome-level rewards provide only sparse supervis
- PaperAMEND: Constraint-Guided Multi-Agent Text Detoxification with Isolated Critics
Text detoxification requires balancing toxicity removal, semantic preservation, and fluency. Existing methods typically optimize an unconstrained scalar objective---enabl
- PaperWhat LLMs Do in the Shadows: Reading Context Reliance from the Unembedding Dark Space
Detecting faithfulness hallucinations in large language models (LLMs) is crucial for their safe deployment in high-stakes domains. Recent approaches address this by contr
- PaperTree-Aware Posterior Distillation for Long-Horizon Agentic Reinforcement Learning
Reinforcement learning with verifiable rewards has become a scalable post-training paradigm for large language models. However, training agents over long-horizon interact
- PaperDo Speech BCIs Need Larger Models? Rethinking Neural Decoding beyond Scaling
Recent speech brain-computer interfaces (BCIs) increasingly rely on large models and complex multi-stage pipelines for neural decoding. However, in speech BCI, where trai
- PaperStructural Affinity: An Algorithm for Coherent Cage-Based Shape Design
Cage-based deformation (CBD) parametrises 3D geometry through a small set of control handles, effectively enabling a variety of tasks from animation and interactive model
- PaperKnowledge-Guided Distributional Prompt Learning with Visual Hierarchy for Zero-Shot Anomaly Detection
Zero-shot anomaly detection (ZSAD) aims to detect anomalies in previously unseen classes using auxiliary images, with applications such as industrial visual inspection an
- PaperChinese Decision: A Family of Language Models for Single-Pass Probabilistic Decision-Making
Many language-based applications require probabilities over a finite set of decisions rather than open-ended responses. We present Chinese Decision, a family of Chinese-l
- PaperLongForge: Measuring and Improving Long-Context Instruction Data via Evidence-Assertion Reasoning Graphs
Existing quality control for long-context instruction-tuning data is a one-shot judgment inside the generation pipeline that leaves only a scalar, revealing neither which
- PaperExplaining Chess and Go in Natural Language
Modern chess engines play far beyond human ability, often choosing moves whose underlying ideas are difficult for humans to understand. We propose an automatic metric for
- PaperAlgorithm Modelization: Transforming Optimization Algorithms into Evolvable Intelligence
Can algorithms be learned and evolved as models, rather than repeatedly redesigned as programs? We explore this question by introducing Algorithm Modelization, a new para
- PaperNearly Linear Private Learning of Littlestone Classes
Differentially private learning aims to learn from data while protecting individual training examples. For binary classification, finite Littlestone dimension characteriz
- PaperCross-Centaur: Modeling Individual Decision-Making Across Psychological Tasks with Language Models
Large language models (LLMs) are increasingly used as computational models of human behavior. Recent models such as Centaur have advanced this goal by fine-tuning LLMs on
- PaperQuAD: Quantitative Assessment via Distribution-Alignment for Qualitative Data Quality Enabled by a Content-Aware Multi-Agent System
Assessing whether qualitative responses collected from semi-structured questions are ready for a particular analysis goal is a persistent challenge. Manual qualitative an
- PaperCIIR - Class-Indexed Interface Representation Learning
Multimodal learning commonly assumes paired or synchronized observations, yet independently collected datasets rarely provide such correspondence. We introduce CIIR, a mo
- PaperCan AI interview? Comparing AI-led to Human-led Chat Interviews
Large language model chatbots have been proposed as AI-interviewers for collecting qualitative interview data at scale, potentially bridging social science's longstanding
- PaperGrounded Credit Assignment in Reinforcement Learning for Multi-Turn Search Agents
Outcome-reward reinforcement learning such as GRPO gives every token of a search-agent rollout the same advantage, although the rollout exercises two capabilities: findin
- PaperLocal proxies for memory-efficient training
Local learning algorithms can reshape resource requirements of artificial intelligence. The memory bottleneck of standard end-to-end backpropagation lies in the need to s
- PaperFrom GAN-Based Models to GPT-5: A Taxonomy-Guided Study of Human Performance in Detecting Deepfake Face Images
Generative models for deepfakes have rapidly evolved from GAN-based architectures to diffusion models and multimodal large language models (MLLMs). However, empirical res
- PaperLexPilot: Benchmarking the Proactive Interaction Ability of Legal LLMs with Laypeople in Chinese Civil Case Consultation
Large Language Models (LLMs) have greatly assisted legal professionals. However, our empirical studies reveal that, when faced with underspecified consultations from non-
- PaperMetaCurate: Evolving Curation Filters for High-Quality Agentic Coding Data
Supervised fine-tuning on agent trajectories is an effective way to improve coding agents, but selecting useful training examples requires more than identifying successfu
- PaperInformation-Geometric Blind Spots of Conformal Test Martingales
Conformal test martingales (CTMs) are e-processes for sequentially testing exchangeability via p-values produced by a conformity function $A$. However, any distribution s
- PaperReliability-Consistent Appearance Modeling for RGB-Infrared Multi-Object Tracking
Recent RGB-infrared multi-object tracking (MOT) methods have substantially improved cross-modal representation learning and multimodal information integration. However, m
- PaperLED: Improving Masked Diffusion Language Models by Lookahead Editing
Diffusion large language models (dLLMs) have emerged as a promising alternative to autoregressive language models, enabling non-autoregressive text generation through par
- PaperScene-Designer: Learning Design Intelligence for Agentic 3D Scene Generation
Generating complete, coherent, and usable 3D indoor scenes from natural language requires strong \textbf{design intelligence}: the ability to design high-quality scenes a
- PaperDomain-specific language alignment of multimodal embeddings towards explainable predictions
Multimodal data are commonly fused into latent representations that improve downstream task performance but are not interpretable, limiting their application in domains t
- PaperWebCoder: Scaling General Frontend Development with Artifact-Grounded Agentic Reinforcement Learning
Real-world frontend development requires agents to compose reproduction, generation, modification, and repair over an evolving application state. Learning a general polic
- PaperTowards a GraphNARX model for structural dynamics
The current paper introduces the GraphNARX model, a graph-based nonlinear autoregressive exogenous model for structural dynamics. The model is built to account for the ge
- PaperDisentangling Language Effects on Tool Admission and Post-Retrieval Safety
LLM agents increasingly use retrieval tools across languages, yet their safety evaluation remains English-centric. It remains unclear whether language affects tool admiss
- PaperRethinking GRPO for Large Reasoning Model Safety Alignment
Large reasoning models (LRMs) exhibit strong reasoning capabilities but remain vulnerable to unsafe outputs. While Group Relative Policy Optimization (GRPO) is widely use
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.