ST-GDance++: A Scalable Spatial-Temporal Diffusion for Long-Duration Group Choreography
arXiv:2603.22316v1 Announce Type: new Abstract: Group dance generation from music requires synchronizing multiple dancers while maintaining spatial coordination, making it highly relevant to applications such as film production, gaming, and animation. Recent group dance generation models have achieved promising generation...
Geometric Mixture-of-Experts with Curvature-Guided Adaptive Routing for Graph Representation Learning
arXiv:2603.22317v1 Announce Type: new Abstract: Graph-structured data typically exhibits complex topological heterogeneity, making it difficult to model accurately within a single Riemannian manifold. While emerging mixed-curvature methods attempt to capture such diversity, they often rely on implicit, task-driven routing that...
Sparsely-Supervised Data Assimilation via Physics-Informed Schr\"odinger Bridge
arXiv:2603.22319v1 Announce Type: new Abstract: Data assimilation (DA) for systems governed by partial differential equations (PDE) aims to reconstruct full spatiotemporal fields from sparse high-fidelity (HF) observations while respecting physical constraints. While full-grid low-fidelity (LF) simulations provide informative priors in...
Cloud-Edge Collaborative Large Models for Robust Photovoltaic Power Forecasting
arXiv:2603.22343v1 Announce Type: new Abstract: Photovoltaic (PV) power forecasting in edge-enabled grids requires balancing forecasting accuracy, robustness under weather-driven distribution shifts, and strict latency constraints. Local specialized models are efficient for routine conditions but often degrade under rare ramp events...
WIST: Web-Grounded Iterative Self-Play Tree for Domain-Targeted Reasoning Improvement
arXiv:2603.22352v1 Announce Type: new Abstract: Recent progress in reinforcement learning with verifiable rewards (RLVR) offers a practical path to self-improvement of language models, but existing methods face a key trade-off: endogenous self-play can drift over iterations, while corpus-grounded approaches rely...
Three Creates All: You Only Sample 3 Steps
arXiv:2603.22375v1 Announce Type: new Abstract: Diffusion models deliver high-fidelity generation but remain slow at inference time due to many sequential network evaluations. We find that standard timestep conditioning becomes a key bottleneck for few-step sampling. Motivated by layer-dependent denoising dynamics,...
Instruction-Tuned, but Not More Verifiable Instruction-Following: A Cross-Task Diagnosis for LoRA Adapters
arXiv:2603.22379v1 Announce Type: new Abstract: Adapters are often selected and deployed based on nominal labels (e.g., instruction-tuned), which implicitly suggest what capability improves after adaptation. We test whether nominal training objectives reliably align with realized cross-task capability gains by evaluating...
Symbolic Graph Networks for Robust PDE Discovery from Noisy Sparse Data
arXiv:2603.22380v1 Announce Type: new Abstract: Data-driven discovery of partial differential equations (PDEs) offers a promising paradigm for uncovering governing physical laws from observational data. However, in practical scenarios, measurements are often contaminated by noise and limited by sparse sampling, which...
A Theoretical Framework for Energy-Aware Gradient Pruning in Federated Learning
arXiv:2603.22465v1 Announce Type: new Abstract: Federated Learning (FL) is constrained by the communication and energy limitations of decentralized edge devices. While gradient sparsification via Top-K magnitude pruning effectively reduces the communication payload, it remains inherently energy-agnostic. It assumes all parameter...
Multimodal Training to Unimodal Deployment: Leveraging Unstructured Data During Training to Optimize Structured Data Only Deployment
arXiv:2603.22530v1 Announce Type: new Abstract: Unstructured Electronic Health Record (EHR) data, such as clinical notes, contain clinical contextual observations that are not directly reflected in structured data fields. This additional information can substantially improve model learning. However, due to their...
A Foundation Model for Instruction-Conditioned In-Context Time Series Tasks
arXiv:2603.22586v1 Announce Type: new Abstract: In-context learning (ICL) allows a model to adapt at inference time by conditioning on examples rather than updating parameters. Existing time-series foundation models use implicit positional context, retrieval, or task-specific objectives, but rarely explicit instruction-conditioned...
With $3.5B in fresh capital, Kleiner Perkins is going all in on AI
The fundraise includes $1 billion for investing in early-stage startups, and $2.5 billion for late-stage growth businesses.
OpenAI’s Sora was the creepiest app on your phone — now it’s shutting down
Though the underlying Sora 2 video- and audio-generation model is scarily impressive, there was not sustained interest in an AI-only social feed.
Spotify tests new tool to stop AI slop from being attributed to real artists
The idea behind the new tool is to give artists more control over which tracks are associated with their name on Spotify.
Arm is releasing the first in-house chip in its 35-year history
Arm is producing its own CPU for the first time. It developed the CPU with Meta, which is also the chip's first customer.
Google TV’s new Gemini features keep fans updated on sports teams and more
Three Gemini-powered features are coming to your Google TV. This includes visual responses, deep dives, and sports briefs.
Talat’s AI meeting notes stay on your machine, not in the cloud
The subscription-free AI meeting notes app is a local-first twist on notetaking tools like Granola.
Doss raises $55M for AI inventory management that plugs into ERP
Doss's AI-powered inventory management system integrates with existing ERP systems. The Series B round was co-led by Madrona and Premji Invest.
Meet the former Apple designer building a new AI interface at Hark
The company said it would design models, hardware, and interfaces in tandem to deliver a "seamless end-to-end personal intelligence product."
Mirage raises $75M to continue building models for its AI video-editing app Captions
Mirage, the maker of video-editing app Captions, has raised $75 million in growth financing from General Catalyst's Customer Value Fund (CVF).
Fast-Slow Thinking RM: Efficient Integration of Scalar and Generative Reward Models
arXiv:2603.20212v1 Announce Type: new Abstract: Reward models (RMs) are critical for aligning Large Language Models via Reinforcement Learning from Human Feedback (RLHF). While Generative Reward Models (GRMs) achieve superior accuracy through chain-of-thought (CoT) reasoning, they incur substantial computational costs. Conversely,...
Does AI Homogenize Student Thinking? A Multi-Dimensional Analysis of Structural Convergence in AI-Augmented Essays
arXiv:2603.21228v1 Announce Type: new Abstract: While AI-assisted writing has been widely reported to improve essay quality, its impact on the structural diversity of student thinking remains unexplored. Analyzing 6,875 essays across five conditions (Human-only, AI-only, and three Human+AI prompt strategies),...
gUFO: A Gentle Foundational Ontology for Semantic Web Knowledge Graphs
arXiv:2603.20948v1 Announce Type: new Abstract: gUFO is a lightweight implementation of the Unified Foundational Ontology (UFO) suitable for Semantic Web OWL 2 DL applications. UFO is a mature foundational ontology with a rich axiomatization and that has been employed in...
Efficient Counterfactual Reasoning in ProbLog via Single World Intervention Programs
arXiv:2603.20505v1 Announce Type: new Abstract: Probabilistic Logic Programming (PLP) languages, like ProbLog, naturally support reasoning under uncertainty, while maintaining a declarative and interpretable framework. Meanwhile, counterfactual reasoning (i.e., answering ``what if'' questions) is critical for ensuring AI systems are robust...
Attention in Space: Functional Roles of VLM Heads for Spatial Reasoning
arXiv:2603.20662v1 Announce Type: new Abstract: Despite remarkable advances in large Vision-Language Models (VLMs), spatial reasoning remains a persistent challenge. In this work, we investigate how attention heads within VLMs contribute to spatial reasoning by analyzing their functional roles through a...
From 50% to Mastery in 3 Days: A Low-Resource SOP for Localizing Graduate-Level AI Tutors via Shadow-RAG
arXiv:2603.20650v1 Announce Type: new Abstract: Deploying high-fidelity AI tutors in schools is often blocked by the Resource Curse -- the need for expensive cloud GPUs and massive data engineering. In this practitioner report, we present a replicable Standard Operating Procedure...
The AI Scientific Community: Agentic Virtual Lab Swarms
arXiv:2603.21344v1 Announce Type: new Abstract: In this short note we propose using agentic swarms of virtual labs as a model of an AI Science Community. In this paradigm, each particle in the swarm represents a complete virtual laboratory instance, enabling...
Reasoning Traces Shape Outputs but Models Won't Say So
arXiv:2603.20620v1 Announce Type: new Abstract: Can we trust the reasoning traces that large reasoning models (LRMs) produce? We investigate whether these traces faithfully reflect what drives model outputs, and whether models will honestly report their influence. We introduce Thought Injection,...
Locally Coherent Parallel Decoding in Diffusion Language Models
arXiv:2603.20216v1 Announce Type: new Abstract: Diffusion language models (DLMs) have emerged as a promising alternative to autoregressive (AR) models, offering sub-linear generation latency and bidirectional capabilities that are particularly appealing for code generation and editing. Achieving sub-linear latency in discrete...
Thinking into the Future: Latent Lookahead Training for Transformers
arXiv:2603.20219v1 Announce Type: new Abstract: Autoregressive language models trained with next-token prediction generate text by sampling one discrete token at a time. Although very scalable, this objective forces the model to commit at every step, preventing it from exploring or...