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
- PaperWhere Latents Belong and How They Flow: Joint Identification of Structural Roles
Latent factors in dynamical systems can play different roles across observations and time. For example, an idea in a group meeting may be expressed by only some participa
- PaperPath to Prior-Data Fitted Relational Models via Learned Latent Multi-table Representations
Prior-data fitted networks (PFNs) show that pretraining on large populations of synthetic tasks can enable generalization to unseen datasets with little or no downstream
- PaperBefore Retrieval Begins: Safety and Tool-Use Decisions in LLM Agents
Large language models increasingly act as agents that call external tools, yet most tool-safety research examines only what follows a tool call. The prior decision of whe
- PaperParetoChat: An LLM-Based Interface for Interactive Multi-Objective Optimization
Multi-objective optimization models are often deployed in settings where decision makers (DMs) must balance some conflicting criteria. In practice, however, stakeholders
- PaperSame Person, Different Advice: Auditing LLM Financial Advice with Repeated Risk-Tolerance Responses
AI financial advisers set a client's stock allocation largely from one stated-risk question, yet people do not answer it the same way twice: in a national US panel, 41% o
- PaperUnifying Embodied Foundation Models via a Model-to-Policy Formulation
Vision-language-action (VLA) models and world-action models (WAMs) have emerged as promising approaches to robot learning and control. These models integrate multimodal p
- PaperAgentic In-Context Learning: What Algorithms Can Transformers Learn in Closed-Loop Interaction?
The learning algorithm view of in-context learning (ICL) studies how fixed-parameter Transformers learn from supplied examples. Language model agents extend this setting
- PaperTriFold: Folding irregular 3D Gaussians into structured latents for 3D Scene Generation
Recent progress in 3D generation has motivated growing interest in compact generative representations of complex 3D scenes. For native 3D Gaussian scenes, however, learni
- PaperDistill Until Divergence: Error-Truncated Hindsight Distillation for Agentic RL
Long-horizon interaction requires agents to make multiple decisions in a changing environment. Outcome-based GRPO lacks fine-grained guidance for intermediate decisions.
- PaperSynerGest: Temporal-Spatial Synergistic Gesture Generation for Dyadic Conversations
Co-speech gesture generation in dyadic conversations for creating immersive virtual avatars remains highly challenging. Existing models often struggle to balance kinemati
- PaperDIFFLET: A Fast Inference Engine for Diffusion Transformer Models on AWS Trainium
On AWS Trainium2, every component of a diffusion model runs as a program compiled ahead of time for fixed shapes, while pipelines differ across models, prompt lengths acr
- PaperSpikeQ: Spike-Guided Post-Training Quantization for Spiking Neural Networks
On neuromorphic chips, spiking neural networks (SNNs) consume far less energy than artificial neural networks (ANNs), but the limited memory of these chips requires low-b
- PaperWhere Does the Performance Go? Understanding and Recovering Performance Regressions in C-to-Rust Translation
Rust is increasingly adopted as a memory-safe successor to C, and transpilers such as \crust{} can migrate entire C projects while preserving their behavior. Preserving b
- PaperGR-OPD: Group-Relative Sequence Credit for On-Policy Distillation
On-policy distillation (OPD) provides token-level teacher feedback, yet common sampled-token updates assign credit locally and omit the effects of earlier actions on subs
- PaperWhen Does Evidence-Graph Structure Predict Answer Correctness? Label-Free Abstention for Structured Retrieval
Retrieval systems return scored answers, but a high score does not show that an answer should be trusted. The proposed training-free abstention method applies the boundar
- PaperFrame-Consistent Feed-Forward 3D Gaussian Splatting from Sparse Unposed Images
Feed-forward Gaussian models have made novel view synthesis almost instantaneous. Feed-forward methods predict Gaussians directly, either in two stages or in a single mer
- PaperWhere Research Ideation Begins: Forward-Citation Supervision for Actionable Limitation Generation
Automated research ideation has advanced rapidly, with multi-agent workflows that generate whole research ideas end to end. These frameworks leave largely unexamined the
- PaperDo Knowledge and Reasoning Oriented Benchmarks Induce Stable Representation Signatures in LLMs?
Internal signatures could support monitoring, adaptive computation, and mechanistic analysis, but benchmark prompts can be separable without any shared computational dist
- PaperTowards Looped Models Done Right, Part I: Topology, Input Injection, Recurrent-State Design
Looped language models reuse physical Transformer blocks across logical depth, but established architectures entangle recurrence placement, input injection, and recurrent
- PaperDistinguishability and Recovery for a Doubly Sparse Spiked Wigner Model
We study distinguishability and recovery of a sparse rank-one signal in a spiked Wigner model with independently sparse noise through a variety of algorithms and paramete
- PaperECHO: Replacing the Compliance Proxy with Response Harmfulness in Optimization-Based Jailbreak Attack
Despite extensive safety alignment, large language models remain vulnerable to jailbreak attacks. Existing optimization-based attacks share a single objective: maximize a
- PaperASE: Attribution-Guided Semantic Evolution for Time Series Forecasting
External text can supply predictive information absent from numerical histories, but its value depends on how it is represented, combined and deployed. We present Attribu
- PaperCausal Value Attribution of Marketing Labels in LLM-Generated Ads: A Deconfounder Approach
As AI-generated content becomes commoditized, economic value increasingly shifts from final artifacts to the upstream expertise used to specify inputs that steer LLM gene
- PaperSemantic-Critical Regions for Video-to-Audio Generation
In real-world videos, sound events are often associated with localized and fine-grained visual cues, such as object motion, object-part dynamics, contact events, and inte
- PaperAdaptation of Computer Use Agents to New Software with User Manuals
Recent advances in multimodal foundation models have significantly improved the ability to operate real-world software through graphical user interfaces (GUIs) using visu
- Paper"Deep lifts": Neural networks can generalize even with the dumbest optimizer
Given a labeled dataset $\{(x_i, y_i)\}_{i = 1}^n$, consider drawing a parameter vector $\hatθ$ uniformly at random from those that interpolate the data within a width-$W
- PaperA Minimal ReLU Classifier on Non-Linearly Separable Data: Convergence and Implicit Bias at and beyond the Edge of Stability
Gradient descent (GD) with large learning rates can successfully optimize neural networks even though classical smoothness-based learning rate conditions are violated. Ye
- PaperEfficient CPU-GPU collaborative MoE inference via Adaptive Expert Assignment
Mixture-of-Experts (MoE) models reduce inference computation through sparse expert activation, but their large expert memory footprint often exceeds GPU capacity, making
- PaperBRICE: Brain-inspired Recurrent Illusory Contour Encoder for Point Cloud Completion
Mainstream point cloud completion methods are unanimously based on deep learning architectures. On one hand, these methods tend to repetitively stacking attention modules
- PaperControlling the Diversity-Quality Trade-Off of LLMs by Merging Models Before and After Alignment
Alignment is known to change the output characteristics of large language models (LLMs). Base models tend to generate more diverse outputs, whereas aligned models tend to
- PaperA Label Noise Robust Algorithm for Graph Data using Neighborhood Label Distribution
Graph Convolutional Networks (GCNs) have demonstrated exceptional performance on graph-structured data. However, their success heavily relies on the availability of clean
- PaperTALLOP: Joint Optimization of Local Training and Communication Compression for Time-Constrained Federated Learning
Minimizing the wall-clock time required to reach a target accuracy is crucial in federated learning (FL), where many applications require frequent model updates as data d
- PaperGOLD: Geometric Optimized Latent Diffusion for Structure-Aware RNA Inverse Folding
Designing RNA sequences that fold into specific 3D structures is a fundamental challenge in therapeutics. Current RNA inverse folding methods typically condition on 3D ba
- PaperA100: A Hybrid Vision Foundation Model for Agricultural Plant Image Analysis
The use of accurate vision models for crop monitoring, disease diagnosis, and plant phenotyping in agriculture is hindered by the lack of expertly annotated data, especia
- PaperPersonaCUABench: Benchmarking Computer-Use Agents Serving Diverse Personas
Computer-use agents (CUAs) are commonly evaluated against fixed task specifications, but users may omit requirements, add constraints, or require approval before conseque
- PaperFrom Approval to Abuse: Privilege Escalation Attacks on Harness-Protected Coding Agents
Coding agents use execution harnesses to constrain the consequences of prompt injection by enforcing permission boundaries. These systems deterministically intercept any
- PaperPrism Attention: Proposal-Refined Index Sharing Mechanism for Efficient LLMs Inference
Long-context decoding in large language models (LLMs) is increasingly bottlenecked by the memory and computation required to attend over an ever-growing Key-Value (KV) ca
- PaperSelf-Evolving Agents Can Repair Failures but Struggle to Generalize from Them
Experience-driven self-evolution offers a promising path for large language model (LLM) agents to continually improve through interaction. Yet existing approaches often r
- PaperUniField++: A Unified Agentic Framework with Loop Reasoning for MRI Field-Strength Enhancement
MRI field-strength enhancement seeks to combine the accessibility of low-field scanners with the image quality of high-field scanners. Yet, existing methods remain prone
- PaperHow Murky Before a VLM Knows It Cannot See? Accuracy, Confidence and Abstention on a Physical Visibility Axis
Robustness studies of vision-language models (VLMs) grade degradation on nominal severity scales ("level 1-5") that carry no physical units, and they rarely ask whether a
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.