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
- PaperFluidGen: Physics-Aware Fluid Video Generation via Motion-Guided Post-Training
Video generation models produce visually compelling motion but systematically fail on fluid phenomena, including smoke, fire, and explosion debris, where outputs lack coh
- PaperBeyond Leaderboards: A Method for Application-Specific Capability Profiling of Large Language Models
Public leaderboards rank large language models (LLMs) in general, but an engineer has to choose a model for a specific application, architecture and cost. This paper pres
- PaperA "feature ODE" describing the learning behavior of shallow MLPs on simple functions
We study the gradient flow training dynamics of two-layer multi-layer perceptrons (MLPs) on anisotropic Gaussian data. Even in this simple setting, solving the dynamics i
- PaperOPDArena: Understanding Learning and Forgetting in On-Policy Distillation
On-policy distillation (OPD) is increasingly used for language model post-training, yet how teacher supervision shapes learning and forgetting remains unclear. We present
- PaperConsistency Training Suppresses Cue Following Without Teaching Cue Selectivity
Language models often change answers because of a cue, a hint such as "I believe the answer is B" that gives no valid evidence. Consistency training (CT) trains a model t
- PaperLatent Projection for Latent Planning
Latent world models let an agent plan in latent space. The planner searches for an action sequence that minimizes a cost, and that cost is often the $\ell_2$ distance bet
- PaperInteractAgent: Agentic Human Motion Interaction with Memory-Augmented Reflection
Long-horizon human-scene interaction requires coordinated spatial reasoning, physical feasibility, and the ability to recover from compounding execution errors. Text-driv
- PaperSpherical Fixed-Point Reasoners: Adaptive Loop Halting on the Hypersphere
Looped (weight-tied) transformers enable adaptive computation by allocating more iterations to harder inputs. Fixed-Point Reasoners (FPRM) achieve this with a damped fixe
- PaperNegation without Confusion: Decomposing Bias and Recomposing Style in Text Embeddings for Negation-aware Image Generation
Negation-aware image generation remains challenging for text-to-image diffusion models, which often struggle with negation due to implicit linguistic biases that are deep
- PaperSampling of Signals on Multigraphs: From Removable and Uniqueness sets to Spectral Proxies
In this paper, we study the sampling of bandlimited signals on multigraphs, where several graphs with different shift operators are defined on the same set of nodes. Sinc
- PaperVisual Memory and Textual Alignment for Cross-Modal Few-Shot Segmentation
Few-shot segmentation (FSS) aims to segment target objects with limited annotated examples. Recent studies have begun to explore large foundation models to improve genera
- PaperThink, Compress, Answer: Reinforcement Learning for Multimodal Grounding via Reasoning Compression
Extended reasoning has substantially improved multimodal large language models (MLLMs) on tasks requiring compositional and relational inference. However, multimodal grou
- PaperACorD: Adaptive Correspondence Discovery for Medical Image Registration
Medical image registration is a fundamental task for aligning anatomical structures across images. Exhaustively searching for point-wise correspondences is prohibitively
- PaperTNVD-SC: Diagnosing Scan Context Failures in Forests with Terrain-Normalized Vertical Distributions
Long-term LiDAR place recognition in forests is difficult because repetitive vegetation and uneven terrain create severe structural aliasing. We diagnose Scan Context (SC
- PaperUncertainty-Gated SHAP-Dirichlet Refinement for MRI-Based Depression Classification
Structural MRI-based classification of major depressive disorder (MDD) remains challenging due to subtle, heterogeneous anatomical changes. We propose uncertainty-gated S
- PaperClean Forcing: Drift-Resistant Autoregressive Video Diffusion with a Frozen Base
Autoregressive (AR) video diffusion models generate streaming video of arbitrary length by conditioning each new chunk of frames on those already generated. However, they
- PaperConfidence-Guided Pseudo-Label Refinement for Unsupervised Cross-Domain Person Re-Identification
Unsupervised cross-domain person re-identification remains challenging because domain shifts generate noisy pseudo labels that are reinforced during iterative adaptation.
- PaperWhere Do the Gaussians Go? Foreground Attraction for Camera-Based Weakly Supervised 3D Occupancy
Camera-based 3D semantic occupancy models can be trained without 3D labels by rendering their predictions into the images and supervising them with 2D pseudo labels. In s
- PaperThe Forward/Inverse Duality of Controlled Emergence:A Computational Design Program from Explanation to Engineering
The macroscopic capabilities of intelligent systems arise from the local interactions of many simple units. When such systems are deployed in the real world, their behavi
- PaperSelecting and Composing Agent Design Patterns: Industrial Case Evidence and Controlled Reference-System Experiments
Agent pattern catalogs describe architectural alternatives, but engineers also need evidence for selecting and composing them. We extend a cognitive-function--execution-t
- PaperConditional Average Treatment Effect Distillation for Hypothetical State-Intervention Targeting Under Budget Constraints
Personalized public-health targeting must capture heterogeneous intervention benefits while remaining interpretable under resource constraints. Flexible causal-effect mod
- PaperMapSteal: Map-based Autonomous Knowledge Stealing Attack Against Large Language Models
Knowledge acquisition from black-box large language models (LLMs) offers a practical approach to adapting smaller student models. However, many existing methods rely on p
- PaperZephyrus-R1: Agentic Reinforcement Learning for Weather Reporting
Reinforcement learning (RL) has emerged as a key method for training AI models in scientific applications, but RL remains difficult when outputs cannot easily be verified
- PaperRecurrent Vision Transformers for Event-Based Spacecraft Pose Estimation Under Slow Relative Motions
Vision-based object pose estimation is vital for conducting spacecraft rendezvous and proximity operations (RPO). Recent research has demonstrated the robustness of event
- PaperWeighted State Souping for Efficient Long-Context Retrieval
State space models (SSMs) combine fast inference and fixed state size with competitive language-modeling performance. Recently, state souping has been proposed as a proce
- PaperCheXFuse: Guided Differential Joint Attention Fusion for Robust Multimodal Chest X-Ray Classification in Data-Scarce Medical Settings
A central challenge in multimodal learning is how to fuse modalities that differ substantially in predictive strength. When one modality provides a much stronger represen
- PaperCurriculum Learning Teaches LLMs Long-Horizon Implicit Reasoning, Up To A Limit
LLMs "reason" by externalizing intermediate steps as tokens through chain-of-thought (CoT), yet even frontier reasoning models hit abrupt performance cliffs on long-horiz
- PaperSafety Offset Learning: When Benign Fine-Tuning Misaligns LLMs
Safety risks from fine-tuning are commonly characterized by the harmfulness of the training data:harmful fine-tuning is considered dangerous, while benign fine-tuning is
- PaperPRISM: Prior Relational Information for Self-supervised Modeling to Enhance Solubility OOD Generalization
Solubility depends on intermolecular interactions between solutes and solvents, and is central to drug discovery, chemical and materials process engineering. Its predicti
- PaperAdversarial Post-Training of Foundation Models for High-Frequency Trading
While autoregressive foundation models trained on limit order book (LOB) data show state-of-the-art performance for market simulation, pre-training with cross-entropy nei
- PaperWhen Better Opportunities Backfire: Service Worker Responses to Parallel AI Deployment in Customer Acquisition
As AI voice agents get deployed in high-volume contact centers, firms can route low-intent leads to AI and allocate high-intent leads to human workers. Drawing on sequent
- PaperText Dominance in Paralinguistic Conflict: Tracing Suppression Through Audio LLM Circuits
Audio LLMs deployed in settings such as crisis hotlines and customer support are only useful beyond speech-to-text pipelines if they use acoustic cues rather than the tra
- PaperCognitive Maps in Large Language Models
It has long been proposed that animals construct cognitive maps to support flexible behavior in novel environments. We tested whether large language models form similar r
- PaperRoboValue: A Fine-Grained Sim-and-Real Benchmark for Unified Evaluation of Robotic Value Models
Robotic value models assess task execution from visual observations and instructions, providing feedback for policy learning and execution monitoring. However, existing e
- PaperHandsOn: A Large-Scale Simulation Benchmark for Generalizable Dexterous Manipulation
General-purpose manipulation requires reliable behavior across embodiments, objects, and task demands. We introduce HandsOn, a composable simulation platform and benchmar
- PaperScaleNav: Scalable Internet Video Pretraining for Language-Conditioned Local Navigation
We study language-conditioned local navigation, where a robot must navigate to a text-specified target visible in its initial observation and stop at the described locati
- PaperWho Takes the Lead? Model Ability and Task-Conditioned Collaboration with Humans
As language-model agents grow more capable, they can carry more of a task without asking anyone for help. Falling reliance on a human partner is easy to read as a failure
- PaperDeep Search in Real-World Web Environments
Despite substantial progress in Deep Search agents, their ability to conduct end-to-end research in real-world open Web environments remains insufficiently evaluated. Unl
- PaperACE-Brain-0.6: Scaling Spatial Grounding for Physical Foundation Models
General-purpose multimodal models, including GPT-6 Astra and Claude Opus 5.5, demonstrate broad capabilities in embodied manipulation. Our analysis indicates that this ge
- PaperLearning from Fleet Experience: A Collective Learning Paradigm for Robots
Experience generated during deployment offers an opportunity for robots to improve policy reliability through learning from their own executions. However, learning throug
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.