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
- PaperProsodic Structure as a Critical Component in Phonemic Language Modelling at BabyLM Scale
Human children learn language from continuous, prosodically structured speech long before they can read, yet almost all language models train on orthographic text. Buildi
- PaperModel Capacity Frontier: A Development Framework for LLM-Supported Social Simulation
Large language model (LLM) agents are increasingly incorporated into agent-based models (ABMs) on the premise that richer, context-sensitive human behavior can improve em
- PaperMargin Certificates for Voting Classifiers under Mixing Dependence
Margin bounds explain why weighted votes generalize after training error vanishes, but dependent observations require concentration arguments that keep the dependence mod
- PaperPronouncing Hard Words: Phoneme Adaptation of a Pretrained Conversational Text to Speech Model
Voice agents built as cascaded automatic speech recognition (ASR)->large language model (LLM)-> text-to-speech (TTS) pipelines increasingly rely on conversational TTS: st
- PaperTorchTPU - A Hybrid Eager/Compiled Architecture for Native PyTorch Execution on TPU
TorchTPU is an open-source collaboration between Google and Meta that introduces a native and principled PyTorch backend for Google TPUs. It enables seamless out-of-the-b
- PaperCoDA: A Human-LM Collaborative Codebook Development Assistant for Domain-Specific Text Annotation
We present CoDA, an open-source human-LM collaborative codebook development assistant that helps domain experts develop annotation guidelines for annotating new variables
- PaperBudgeted Bayesian Bandits for Future Utilization
The multi-armed bandit problem models the trade-off between exploration and exploitation. In this paper, we study the variant where exploration has a hard budget and prec
- PaperNV-Generate-Body: 3D Latent Diffusion Model forControllable Anatomy, Tumor, and Demographic Body Mask Synthesis
Curating large labeled CT datasets is expensive and constrained by patient privacy. We present NV-Generate-BodyMask, a 3D latent diffusion model that synthesizes whole-bo
- PaperPreservation and loss of algorithmic structure in experimental diffusion of joint-action norms
Everyday norms of social interaction - e.g. norms of sharing space, taking turns, or queuing - are essential to large societies, offering structured procedures for common
- Paperlepidoptera: A Domain-Agnostic Engine for Causal Simulation with Mixed Variable Types, Vine Copula Dependence, and Individual-Level Counterfactual Propagation
lepidoptera is an open-source R and Python package for simulation from structural causal models with heterogeneous variable types. The package is built around a typed mec
- PaperSequence-to-Sequence Neural Surrogate Modeling of Transient Responses in High-Speed Links with Variable Design Parameters
This paper presents sequence-to-sequence (seq2seq) neural surrogates for high-speed transient response modeling and signal integrity analysis in fixed and variable design
- PaperEGGHead: Efficient Generalizable Gaussian Heads from a Single Image
Creating photorealistic human heads typically involves trade-offs between representation power, efficiency, and generalizability. Traditional mesh-based solutions relying
- PaperFrom Spectrograms to Shallow Speech SSL: Audio-Frontend Design for Generator-Disjoint and Low-Latency Audio--Visual Deepfake Detection
Video-mediated conversational systems rely on synchronized speech and facial video, making audio--visual input integrity important for reliable perception. We study audio
- PaperContinual Test-Time Learning with Evolution Strategies
Large language models increasingly operate in open-ended environments, where they are expected to continually adapt to evolving tasks and distributions, often without acc
- PaperInside the Loop: A Mechanistic Study of Weight-Tied Transformers on Depth-Bound Algorithmic Tasks
Solving algorithmic tasks with many sequential steps typically requires scaling up transformer depth or chain-of-thought length, incurring unfavorable parameter and infer
- PaperAccelerating Wildfire Hazard Mapping Across Canada with an AI Surrogate Modelling Framework
Canada's increasing wildfire activity requires frequent national hazard mapping to guide proactive mitigation, including fuel management, land-use planning, infrastructur
- PaperA Conditional No-Hair Theorem for Transformers: How Language Models Forget Their Prompt
We ask how much an autoregressive transformer retains of its prompt after generating $t$ tokens. Consider two different prompts followed by the same continuation text, so
- PaperThe Weight of Teamwork: Does Communication Structure Help LLM Scientists Search for Scientific Laws?
Team performance is often reported as one delivered score, even though that score is produced in two stages: a system generates candidate answers and a selection rule ret
- PaperReducing double-dipping in single-cell topic models with three-way count splitting
Topic models learn gene programs from single-cell RNA sequencing (scRNA-seq) data, and the same counts are then used to test which genes and donors are associated with th
- PaperRecording-Aware Evaluation of Multimodal OT Intrusion Detection
Machine-learning-based intrusion detection systems (IDSs) for operational technology (OT) are commonly evaluated on benchmark datasets in which normal and attack data are
- PaperData-Driven Resource Aggregation for Scalable Digital Twin and Simulation Model Generation
As industrial digitization accelerates, the use of digital twins has become widespread. However, modern manufacturing systems are highly dynamic and frequently reconfigur
- PaperOn the Selectivity of Generative Models in Structure-Based Drug Design
Designing small-molecule drugs that selectively bind to a target protein while avoiding unintended interactions with other proteins is essential for reducing side effects
- PaperPrefix-Tuning for Arbitrary Output Sequences on Pretrained Transformers
Prefix-tuning is a parameter-efficient fine-tuning method for large language models (LLMs) that steers model outputs by prepending task-specific prefix representations to
- PaperHAVANA: A Hierarchical Video-Action Model for Vision-Language Navigation
Vision-Language Navigation (VLN) requires long-horizon instruction-consistent planning and short-horizon local planning in current geometry. Video-action models (VAMs) of
- PaperDo LMs Know What Variables Do? Interpreting Code Representations via Variable Roles
Variable roles describe recurring behaviors such as accumulation, traversal, and retaining the best candidate encountered. We use Sajaniemi's independently defined taxono
- PaperGraph-Regularized Synthetic Control for Stable Counterfactual Estimation under Donor Redundancy
Synthetic control methods estimate counterfactual outcomes by weighting untreated donor units to match a treated unit before treatment. In recent applications, however, t
- PaperLooped GNNs Beyond Fixed Depth: Graph Size Generalization and Parameter-Efficient Adaptation
Generalizing from small graphs to larger ones can require computation beyond the depth of a neural model used during training. We study target tasks that admit a common l
- PaperInterpretability of AI weather models via intermediate decoding
AI weather prediction models are often regarded as black boxes. Despite their impressive skill, there is little understanding of how the input data is processed during in
- PaperBLANC: Adaptive Temporal Scheduling for Sign Language Production
Sign language production (SLP) aims to synthesize expressive signing motion from written text. Modeling signing motion presents two key temporal challenges. First, fine-g
- PaperJoint, Decoupled, or Agent: When Each Multimodal Alignment Paradigm Wins
Jointly pretrained multimodal encoders are a common way to combine modalities, while alternatives integrate their information during downstream training or inference. Whe
- PaperCache2LoRA: Understanding and Improving Context Internalization
Context-to-LoRA methods encode documents as low-rank parameter updates, allowing language models to answer without retaining the source text in their decoding context. Ho
- PaperHierarchical and Query-Aware Visual Token Pruning for High-Resolution LVLMs
High-resolution Large Vision-Language Models (LVLMs) preserve critical, fine-grained visual details by encoding a global thumbnail alongside multiple local crops. However
- PaperBiNar: Bitstream Native Restorer for Bitstream-corrupted Image Restoration
Bitstream-corrupted image restoration (BCIR) aims to reconstruct faithful images from corrupted compressed bitstreams. However, corruption occurs in bitstream-domain may
- PaperDoes AI-Assisted Development Homogenize Software? An Empirical Study of Code Similarity, Quality, and Evolution
AI-assisted software development is evolving from interactive LLM assistance toward agentic systems that autonomously perform software engineering tasks, yet the effects
- PaperPersistent Memory and Iterative Improvement in an LLM Agent for Chinese-Character Drawing
Does persistent memory accumulated from previous attempts help an LLM agent solve new problems, and does memory design affect that benefit? We study programmatic Chinese-
- PaperFinitely Verifiable Segmentation: Decidability for Every Tokenizer with a Finite-State Verifier
A segmentation policy assigns to each byte string at most one segmentation into tokens. Call it finitely verifiable when a finite automaton over marked strings, bytes pai
- PaperOR-License: Evaluating LLM Agents as Real-World Operations Research Practitioners
Can large language model (LLM) agents deliver expert-level operations research (OR) solutions directly from original client materials, without prior expert reformulation?
- PaperCoopshift: Post-Training Amplifies The Memory Curse In LLM Cooperation
How does post-training change cooperation during repeated interaction? Within each of seven released model lineages, we compare pretrained (Base), supervised fine-tuned (
- PaperGLOW: General Linear Models Optimized with Ward's Method
Neuroimaging seeks brain regions whose imaging features correlate with variables of interest (e.g., diagnosis, age), usually via the General Linear Model (GLM). Region-Ba
- PaperLocation, Location, Generation: Where You Ask Matters for Generative Engine Optimization
Generative search engines answer local and commercial questions with a written answer and a few cited sources. A growing practice of generative engine optimization (GEO)
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.