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…
Thursday 15 October
- PaperLearning Self-Orchestration in Decentralized Agent Swarms
The capabilities of an agent swarm depend on both its individual members and how they coordinate. Yet existing multi-agent systems often train agents within fixed orchest
- PaperAVC-Reward: Event-Centric Audio-Video Consistency Evaluation
As joint audio-video generation models become more capable, they can generate audio-visual scenes exhibiting three forms of complexity: multi-event composition, multi-lay
- PaperNot Just a Subject: Capturing Adaptive Scene-Specific Variance for Visual Storytelling
Recent advancements in diffusion models have significantly improved text-to-image generation, enabling their application to visual storytelling, where coherent image sequ
- PaperA team of Gemini 4 Argon agents beats Minecraft
We placed four Gemini 4 Argon agents in a sandboxed Minecraft survival world and gave them one goal: defeat the Ender Dragon. Each agent controlled a player via an open-s
- PaperLearning to Steer LLM Agents and Multi-Agent Systems
Large language model (LLM)-based agents and multi-agent systems increasingly tackle complex tasks through long-horizon tool use and inter-agent collaboration. However, th
- PaperMindEval2: Clinically Grounded Patients and Rubrics for Evaluating Language Models in Mental Health Support
With people increasingly turning to AI chatbots for mental health support, the need to evaluate these tools is becoming more pressing. Recent benchmarks attempt to mimic
- PaperGrid-Bench: Can LLMs Predict How Discrete Worlds Change?
Spatial instructions describe how to move objects, transform regions, or modify their surroundings. When several operations are applied in sequence, each acts on a config
- PaperVelox: Spatial Memory Makes World Models Efficient
Video world models turn actions and camera motion into long visual rollouts, making video a natural interface for interactive simulation. Such interaction requires respon
- PaperARC-SORT: Adaptive, Robust, Compensated Multi-Object Tracking with Interacting Multiple Models
Multi-object tracking in sports broadcasts is hard for two reasons: athletes move fast and change direction abruptly, and the camera pans and zooms at the same time. We p
- PaperKnowledge That Is Linear Before Fine-Tuning Generalizes After It
Not all facts a language model can recall support further learning equally well. We distinguish active facts, which support generalization beyond their own recall, from i
- PaperTesting the Planning Claims of LLM-Based Agents against Formal Semantics
LLM-based agents are increasingly credited with the competences of practical reasoning: planning, monitoring, and correcting their own actions. Their success is attribute
- PaperAI Consilium: a Benchmark of LLM Clinical Multidisciplinary Second Opinions
Large language models (LLMs) can generate differential diagnoses for complex cases, but a useful second opinion must also be factually grounded, clinically coherent, acti
- PaperPrivate Retrieval Augmented Generation via Random Projection
Retrieval-Augmented Generation (RAG) enhances the capabilities of large language models (LLMs) by querying external structured knowledge. However, it can also introduce p
- PaperBackward Compatibility in Zero-Bit Neural Audio Watermarking
Neural watermarking systems are typically trained as tightly coupled embedder-detector pairs and implicitly assume static deployment. In real-world deployments, embedders
- PaperGrounded Human-Attributed Description and Activity Recognition in Videos
Understanding characteristics and activities of individuals in complex multi-person environments is crucial for real-world applications. However, existing datasets often
- PaperMulti-Target Few-Shot Prompting with Diffusion Language Models
Few-shot prompting is useful when instructions and rewards are hard to specify. One such application is editing by example, where a demonstrated formatting change or API
- PaperTowards Continual Learning: Mitigating Forgetting With Subspace Tuning
Large language models (LLMs) acquire new skills through fine-tuning, but it can destroy capabilities they already have: catastrophic forgetting remains a central obstacle
- PaperCAT-alyzing Honesty: Continuous Adversarial Training for Transferable LLM Honesty
Large language models (LLMs) are becoming prevalent in scenarios where honesty is critical. However, despite alignment training, these models still exhibit dishonest beha
- PaperFrom Parallels to Divergence: Language Models' Learning of Action Nominal Constructions
Action nominal constructions (ANCs) express events in nominal form, with their argument marking following patterns found in clauses or ordinary noun phrases. In this pape
- PaperEliteReplay: Preserving Diverse Solutions in RL Post-Training via Quality-Diversity Search
Reinforcement learning has become a common post-training technique to improve the accuracy of LLMs on verifiable tasks. However, such training can narrow the set of solut
- PaperImproving Environment-Agnostic Agents: The Role of Scaffolding
Agents built on stronger language models may increasingly construct useful procedures for themselves, reducing the advantage of developer-supplied scaffolding. We investi
- PaperLearning Rational Strategies for Temporal Objectives in Multi-Agent Systems
We study rational synthesis for stochastic multi-agent systems with unknown dynamics, where each agent is equipped with its own probabilistic temporal objective specified
- PaperAsking Smarter Questions: Targeted Active Preference Learning for Underspecified Rewards
Reward learning typically assumes the human's input covers everything that matters for the task. In practice, humans can only attend to so much at once, so their teaching
- PaperRouting Policy Optimization for Online Diffusion Reinforcement Learning
Reinforcement learning can align visual generators with reward signals beyond their pretraining objectives, but existing score-function methods typically introduce stocha
- PaperLEASH: Uncertainty-Aware Weak-to-Strong Escalation and Oversight for Computer-Use Agents
Computer-use agents increasingly tackle long-horizon tasks, where running a frontier model at every step is expensive and a small open-weight model alone often fails. Wea
- PaperProgressive Misalignment Can Emerge from Benign Recursive Self-Distillation
Training models on their own outputs has attracted widespread attention as a possible route to advance AI capabilities. One prominent approach is self-distillation, where
- PaperHarness-Delta Attribution: Dissecting Gains From Harness Evolution
Harness evolution automatically optimizes the prompts, skills, tools, and orchestration code around a fixed-weight model, offering a way to improve agentic systems withou
- PaperMJev-Spatial: System One Spatial Intelligence via Native Attention Matching
Spatial intelligence lets an agent perceive and act in the physical world, and many of its judgments must be made at interaction rates: which spatial relation holds, how
- PaperLibrarian Agents: Training LLMs to Curate Long-Context Workspaces that Anticipate Future Queries
Reasoning over long document contexts remains a challenge for large language models (LLMs). Standard retrieval methods are inherently reactive, bottlenecking agents with
- PaperUnsupervised Clustering of Public Transport Vehicles Using Deep Morphological Features and Color Histograms
Surveillance cameras along urban roads produce large volumes of unlabeled video that could support the monitoring of public transport, but grouping the observed vehicles
- PaperX-RIC: An Agentic RAN-Intelligent Controller Benchmark for Enhancing Reinforcement Learning
The O-RAN ALLIANCE introduces architectural flexibility through disaggregation and AI-driven control. While the RAN Intelligent Controller (RIC) enables centralized optim
- PaperBeyond Pairwise Repulsion: Collective Diversity via Determinant Maximization in Diffusion Sampling
Strong guidance in text-to-image (T2I) diffusion models concentrates sampling toward high-density modes of the conditional distribution, collapsing independently sampled
- PaperSCOPE: Semantic Bounded Credit Optimization for Prompt Engineering in Text-to-image Generation
Reinforcement learning (RL) enables language models to improve text-to-image (T2I) generation by rewriting prompts for a frozen image generator. Existing methods typicall
- PaperAuthor-in-the-loop Agentic Reproducibility Auditing for a Machine Learning Conference
Reproducibility checks during peer review require a shared understanding of what authors' code is expected to reproduce. We present an author-in-the-loop collaborative au
- PaperBaselines and Score Centering in Policy Gradient Estimation
Reinforcement learning has become a widely used approach to post-training large language models. In a typical implementation, learning is off-policy: The policy generatin
- PaperPolitical Narratives in the 2024 Moldovan Presidential Election: Stance, Amplification, and Influence
Social media platforms play a central role in shaping political discourse during elections, particularly in geopolitically contested regions. We study how political narra
- PaperTopology-Inspired Fine-Tuning for Wind-Field Super-Resolution
Scientific super-resolution (SR) models are typically optimized with pointwise reconstruction losses, yet scientific interpretation often hinges on extrema, connected reg
- PaperFPG-Seg: Annotation-free Retinal Vessel Topology Segmentation
State-of-the art approaches to retinal vessel segmentation typically require extensive annotations, a highly time-consuming process, reliant on clinical expertise. We pre
- PaperDenoising Textures is a Different Ballgame Altogether!
The human brain effortlessly deciphers colors and textures from visual stimuli and reconstructs the world around us, yet preserving such details remains challenging in im
- PaperBitSparse: Compact Activation Storage for ReLU Feed-Forward Networks
Reducing memory use in large language model (LLM) training is an ongoing challenge. Activation checkpointing saves memory by recomputation, while lossy compression change
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.