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…
Tuesday 20 October
- PaperRacer: Hunting GPU Kernel Bugs with Symbolic Equivalence Checking
GPU kernels are critical to the performance of today's AI services, yet the same operators are rewritten repeatedly: for each GPU generation, numeric format, serving regi
- PaperRegion-Specific EEG Classification of Hypnotic Susceptibility Using a Sliding-Window 2D CNN: A Subject-Independent Evaluation
We investigate whether a 2D Convolutional Neural Network (CNN) trained on minimally preprocessed EEG signals can classify hypnotic susceptibility across distinct brain re
- PaperAfter the Attacker Leaves: Benchmarking Carryover Attacks on LLM Agents
Modern LLM agents persist state across sessions via two channels: long-lived memory files silently prepended to the system prompt, and scheduled tasks waking the agent wi
- PaperWorldSR: Harnessing World Knowledge Search for Grounded Image Super-Resolution
Generative-prior-based super-resolution (SR) methods leverage implicit knowledge learned from large-scale models to enhance low-resolution inputs. However, such priors ar
- PaperDISTRACT: Degradation-Indexed Study of Textual Reference Across Competing Targets
Vision-language trackers (VLTs) accept descriptions intended to assist tracking, but accepting text does not establish that its content changes tracking decisions, partic
- PaperCode2Video-Compass: A Comprehensive Benchmark for General-Purpose Code-Based Video Generation across T2V, I2V, and V2V
Code-based video generation offers fine-grained control, targeted editing, and component reuse compared with direct video generation. This approach requires multimodal la
- PaperBrain2Vec: A Self-Supervised 3D Foundation Model for Structural Brain MRI
Deep learning models have become essential tools in medical imaging, yet training them end-to-end for diverse tasks remains challenging due to limited labeled data and co
- PaperA Multi-Agent Framework for Automated Machine Learning with Evidence-based Planning for Medical Image Analysis
Deep learning has become the default tool for medical image analysis, driven by the open-source movement. However, achieving the best performance on a given task remains
- PaperRewards for Budget-Aware Multi-Turn Agents That Adapt to Arbitrary Test-Time Constraints
Large language model agents are often given an inference budget and asked to maximise success within it. A multi-turn agent has to allocate this budget across many enviro
- PaperThe Instruction Tax on Factual Recall: Base Models Can Beat Their Instruction-Tuned Counterparts
We present our solution to the AKBC LM-KBC 2026 Shared Task, where we achieved a score of 0.6836 on the official leaderboard, more than double the baseline of 0.2964. Thi
- PaperDIVE: Benchmarking Full-Duplex Interaction with Visual Engagement in Continuous Streams
Recent advances in multimodal large language models (MLLMs) have substantially improved spoken interaction and video understanding. Existing online and streaming benchmar
- PaperStreamEval: Evaluating Interactive Streaming Video Generation Models
As streaming video generation advances, enabling real-time interaction with generated video is becoming increasingly important. We introduce StreamEval, a unified benchma
- PaperMAS-Guard: Unified Guardrails from Individual Agents to Multi-Agent LLM Systems
Agentic AI extends large language models (LLMs) from generating responses to planning and executing complex workflows, substantially expanding their utility while exposin
- PaperWhen Copying Is Hard: Copy-Constrained Decoding for Exact Span Reproduction
Precisely reproducing a target span verbatim within a long context is a fundamental capability test for LLMs: even when the target string is present in context, models of
- PaperSelf-Credit: Credit Assignment for Long-Horizon Agentic RL via Intra-group Rescaling
LLM agents are commonly trained with RLVR, but the sparse nature of typical RLVR rewards makes credit assignment challenging, especially for long-horizon tasks. We propos
- PaperVisualEvolve: A Skill Self-Evolution Framework for Visual Reasoning
Visual tool use enables vision-language models (VLMs) to acquire task-relevant evidence, but its effectiveness can be limited by predefined visual operations and the tool
- PaperRACE: RoPE-Aligned Attention Compression Based on Query-Key Activation Energies
Head-dimension compression can reduce the memory required by the key-value (KV) cache, but existing methods often reconstruct full-dimensional representations during infe
- PaperRACE: Learning Multimodal Search through Referential Abstraction and Compositional Evidence
Training multimodal search agents requires tasks that make visually grounded search necessary for determining the answer. Textual identity clues and unused target evidenc
- PaperCAPSafe: A Benchmark for Contextual Action and Plan Safety Reasoning in Embodied Agents
Reasoning about safety is essential for embodied agents powered by large language models (LLMs). We introduce the Contextual Action and Plan Safety benchmark (CAPSafe), d
- PaperObject-Oriented Harness: Evolving Agent Harnesses through Object-Oriented Design
Agent harnesses are executable code that specifies the prompts, tools, and control flow around a language model. A single global harness can struggle with heterogeneous t
- PaperDon't Skip the Baseline: A Controlled Comparison of Dynamic Expert Skipping in MoEs
A growing body of work proposes dynamic expert-skipping methods for Mixture-of-Experts (MoE) models that adjust the number of experts activated per token during inference
- PaperRelative Representations Enable Portable White-Box Monitoring Across Language Models
Independently trained autoregressive language models often acquire similar capabilities, but it remains unclear whether their internal representations organize behavioral
- PaperContext-Aware Prompt Injection Detection via Small Language Models in RAG Pipelines: nokast-secureRAG
Local Retrieval-Augmented Generation (RAG) systems are vulnerable to indirect prompt injection and retrieval poisoning, where malicious instructions in retrieved content
- PaperFALCA: Falsification-Aware Reinforcement Learning with Hierarchical Credit Assignment for Long-Horizon Deep Search Agents
Long-horizon deep search requires LLM agents to iteratively decompose complex information needs, gather evidence from external sources, and maintain a reliable research s
- PaperConfessions of a Masked MDP
In reinforcement learning, one presumes the action set to be known ahead of time, and, thus, one must know if any state-action pairs are not permissible ahead of computat
- PaperCountVideoBench: A Benchmark to Evaluate Prediction Biases on the Object Counting task by Video-Language Models
Object counting in videos remains a poorly characterized capability of multimodal large language models. Counting questions are included in many existing VideoQA benchmar
- PaperBeyond the Point Mass: Acceptance-Derived Weights and Distributional Losses for Speculative Decoding
In speculative decoding, a lightweight draft model proposes tokens that the target model verifies in parallel, speeding up generation without changing the target distribu
- PaperS-Agent 2.0: Spatial Reasoning with a General Coding Agent
Spatial reasoning asks a model to work out where objects are in 3D space, how they relate to one another, and how they move. Agentic VLMs have recently brought large impr
- PaperRayCo4D: Ray-Conditioned Continuous Motion Model for Monocular 4D Dynamic Reconstruction
Reconstructing dynamic 3D scenes from monocular video requires inferring motion from noisy and intermittently visible observations. Long-range tracks provide valuable geo
- PaperGated Prototype Transfer for Zero-Support Medical Vision Language Model
Realistic few-shot adaptation of medical vision-language models (VLMs) can leave low-prevalence classes without any labeled support. The training-free SS- Text+ solver re
- PaperCharacterizing Cross-Relay Generalization Failure in Machine Learning-Based Power System Protection
Machine learning-based fault detectors are often evaluated at the relay locations used for training, although local voltage and current measurements vary across power net
- PaperAuto-Director: Leveraging Multi-Agent Collaboration for Autonomous Video Editing
Autonomous video editing from open-world resources remains a challenging problem in multimedia content creation. Retrieval-based methods are constrained by fixed source m
- PaperDeclineCraft: A RAG Abstention Benchmark for Jointly Measuring Combined Retrieval and Parametric Knowledge
Reliable retrieval-augmented generation (RAG) requires recognizing when neither retrieved documents nor parametric knowledge supports an answer. We introduce DeclineCraft
- PaperHistoLoop: Iterative Contextual Inference with a Looped Transformer for Histology-Based Spatial Gene Expression Prediction
Predicting spatial gene expression from H&E images offers a scalable complement to experimental spatial transcriptomics. However, despite progress in spatial context mode
- PaperBeyond a Single Sentiment Score: Topical and Affective Dimensions of Emoji Meaning on Twitter
Emoji are widely treated as compact affective tokens whose meaning is summarised by a single sentiment score. We argue that this picture is incomplete. From a corpus of 1
- PaperIdentifying Dependent Components from Multi-domain Linear Mixtures
We study a linear mixing model with dependent latent components, assuming multiple data domains. Most existing models assume that the components are independent or at lea
- PaperObservation Assimilation Transformer: Probabilistic Weather Analysis from Sparse Station Observations
We present the Observation Assimilation Transformer (OAT), a geometry-aware neural process that corrects and refines a prior numerical weather prediction (NWP) field into
- PaperIs Sycophancy a Form of In-Context Updating?
Factual sycophancy, a language model's deference to a user's false beliefs, is usually understood as a bid for the user's approval at the expense of truthfulness. We argu
- PaperPACE: Plan, Attend, Check, and Emit for Training-Free Response Timing in Streaming Video Understanding
Streaming video understanding requires a model to decide not only what to answer but also when to answer. Evidence arrives progressively, and recent benchmarks identify p
- PaperManifold-Informed Neural Networks for Low-Label ECG Electrolyte Inference
Physics-informed neural networks (PINNs) supervise on the residual of a known differential operator. Many high-stakes inference problems admit no such operator: clinical
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.