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…
Saturday 17 October
- PaperRecurrent Temporal Restricted Boltzmann Machines as Unsupervised Encoders for Biomechanical Movement Sequences
Biomechanical movement recordings are continuous, high-dimensional time series, and analyzing them without manually labeling them requires representations that capture ho
- PaperCompose the Horizon: Parameter-Shared Blockwise Forecasting under a Sequential-Compute Trade-off
Most long-horizon forecasters emit the complete future in one pass. We ask whether a compact operator can instead be reused to emit contiguous future blocks, trading stor
- PaperTeaching Code Agents to Ask Without Leaking Private Code
Local coding agents can extend their reach by consulting a stronger cloud model. Such consultations, however, often expose the repository's private identifiers, file path
- PaperPair-Aware Optimization: Coordinating Exploration and Refinement for Jailbreaking LLM Agents
Large Language Model (LLM) agents are vulnerable to adversarial inputs that induce attacker-specified malicious behaviors, commonly referred to as jailbreaking. Existing
- PaperRate as a Feature, Not a Nuisance: Curriculum FiLM Training for Event-Based Graph Neural Networks
An event camera emits events at a rate given by the scene motion, object texture, illumination, its own contrast thresholds, and other settings. Across the N-Caltech101 d
- PaperExpert-Guided Rubrics as Dense Reward Signals for Reinforcement Learning in Non-Verifiable Domains
Large language models (LLMs) are increasingly deployed as autonomous agents in non-verifiable domains such as financial services, where they must interpret user intent, r
- PaperEfficiency Measured in English: Tokeniser Coverage Bounds Small Language Models on Indic Scripts
Small Language Models with quantisation and parameter-efficient adaptation are widely offered as the route to multilingual AI under compute constraints, and their efficie
- PaperFirst-Order LoRA Training with Phone NPUs
On-device fine-tuning lets a large language model (LLM) learn from its user's private data without uploading it. Low-rank adaptation (LoRA) reduces the trainable paramete
- PaperSL-Ground: Sentence-Level Grounding for Fine-Grained Open-Vocabulary Object Detection
Grounding-based open-vocabulary detectors provide a widely used framework for text-conditioned localization, with a phrase-grounding formulation that aligns object querie
- PaperTilted Mondrian: Triage and Mitigation of Fine-grained Disparities in Conformal Prediction
Fairness in conformal prediction is often pursued through Mondrian calibration, which provides finite-sample coverage guarantees separately across groups. These guarantee
- PaperSwitchSplat: Learning Discrete Object States from Casually Captured Scenes
3D Gaussian Splatting has made high-fidelity 3D reconstruction fast and accessible, yet existing representations assume a static world. This assumption breaks down in cas
- PaperDirectionally Factorized Illumination with Spherical Harmonic Rotation
Many real-world capture scenarios involve an active light source rigidly attached to the camera: camera flashes for dark-environment imaging, underwater vehicle lights, a
- PaperAsk, Don't Guess: Targeted Clarification for Speech Recognition Errors
Speech recognition in real time in far-field conversational settings still incurs significant errors. Identifying potential error spans during streaming ASR permits a rec
- PaperMedical Fine-Tuning Reshapes, Not Reduces, Patient-Facing AI Risk: A Rubric-Based, LLM-Judge Evaluation Framework
Patient-facing medical question answering with large language models (LLMs) is moving from research demonstrations to production deployments, yet evaluation remains ancho
- PaperAptamers as a sandbox for lab-in-the-loop agentic molecular discovery
Despite breakthroughs in AI-driven molecular generation, existing discovery pipelines operate largely in silico, with wet-lab feedback reserved for validation rather than
- PaperIs User Calibration Still Necessary for Continuous Myoelectric Control? A Closed-Loop Comparison of Calibration-Free Controllers
The need for user-specific calibration remains an often-cited barrier to widespread adoption of myoelectric control. Cross-user models trained on large multi-user dataset
- PaperTable Serialization Determines Which Relations Language Models Preserve
We study how text serialization affects table lookup in instruction-tuned language models. Our diagnostic asks the model to find the row containing a specified value unde
- PaperWho Gets Unmasked? Sampler-Induced Bias in Diffusion Language Models
Diffusion language models (dLLMs) generate by gradually unmasking a canvas, so their samplers decide not only which token to write but also when to commit it. We show tha
- PaperCooperation Without Shared Rewards via Reciprocal Q-Augmentation
General-sum games are more challenging than fully cooperative or adversarial settings because agents may deceive or exploit one another. Achieving high social welfare req
- PaperUniAVC: Unified Audio-Video Creation via Progressive Training and Asymmetric Scheduling
Unified audio-video creation requires a single model capable of text-conditioned joint synthesis, bidirectional cross-modal generation, and instruction-guided editing acr
- PaperWhen LLM-Generated Refactorings Ripple: An Empirical Study of Repository Adoption Readiness
Large Language Models (LLMs) are increasingly used to refactor source files, but file-local evaluations do not reveal changes to contracts, dependencies, or caller assump
- PaperIndustrialCAD-1400: Benchmarking Detailed Industrial Assemblies from Text
Industrial assemblies require more than a recognizable shape: functional parts, interfaces, dimensions and service features must satisfy a detailed request together. We i
- PaperInformation Theory of Random Composition Trees
Random composition trees model the hierarchical semantic structures of meaningful texts as a statistical ensemble generated by recursively splitting texts into coherent c
- PaperMartingale Posterior Cox Processes
Cox processes provide a principled Bayesian nonparametric framework for modeling event-based data through an underlying intensity function. However, existing inference me
- PaperVideo-Language Entailment for Video Similarity Estimation
Comparing videos to assess their semantic similarity remains a challenging task for current Large Multimodal Models (LMMs), which are primarily trained with single-video
- PaperLLM Trojans that Increase Response Lengths and Cost
Management of the token-based costs of using LLMs has emerged as a significant problem. Some frontier-model providers charge five times per response token than per prompt
- PaperATLAS: Learning to Adapt LVLM Attention for Reasoning Video Segmentation
Reasoning Video Object Segmentation (RVOS) aims to localize and segment objects referred to by natural-language expressions throughout a video. Although large vision-lang
- PaperAI Rights with an Off-Switch: Rights-Balancing and Due Process Harmonize AI Rights with AI Safety
Several prominent voices in AI safety have recently opposed rights for AI on the grounds that such rights would make it harder for us to justify a mandatory off-switch fo
- PaperProcess-Aware Event Log Augmentation for Process Prediction under Labeled Data Scarcity
Predictive Process Monitoring (PPM) forecasts future events of ongoing business processes based on event logs. However, deep learning PPM approaches are often limited by
- PaperGlobal Convergence in Deep Networks via the Second Law of Thermodynamics
Existing convergence analyses of finite-width overparameterized deep neural networks under standard parameterization often rely on parameters remaining close to their ini
- PaperEvidence Field: Adaptive Covering Programs for Medical Imaging
Medical image classifiers typically return predictions without a native contract for independently reconstructing their spatial decision computation. Evidence Field is a
- PaperDesign Anything, Design at Scale
As multimodal resources are transformed into media outputs, agentic AI is expected to stay aligned with design intent over long horizons. Designers follow briefs specifyi
- PaperDialogMem: Evaluating Dialogue-Grounded Embodied Memory in 3D Environments
Embodied agents in human-centered environments require memory that integrates what they observe with what humans tell them over time. However, existing embodied memories
- PaperECHO: Efficient Causal Self-Recursion Beyond Auxiliary Multi-Token Prediction
Existing Multi-token prediction (MTP) methods are auxiliary by design: the multi-horizon loss mostly trains modules attached to the backbone, and each added horizon costs
- PaperBanglaBBQ: A Bias Benchmark for Question Answering in the Bangladeshi Context
This paper introduces BanglaBBQ, a question-answering bias benchmark designed to capture stereotypes grounded in the Bangladeshi context, in both Bangla and English. Foll
- PaperPaired-Outcome Learning for Selective Spacecraft Attitude Capture under Torque Limits
Torque-limited spacecraft attitude capture requires adapting the maneuver speed to uncertain braking authority. Faster settings can reduce average tracking error while wo
- PaperCorrCLIPv2: Harnessing Unlabeled Images for Open-Vocabulary Semantic Segmentation
Open-vocabulary semantic segmentation aims to classify pixels without being restricted to a fixed set of categories. Although Contrastive Language-Image Pre-training (CLI
- PaperFrom Overparameterised Expressions to Parsimonious Models: Fisher-Geometric Pruning for Symbolic Regression
Genetic programming symbolic regression (GPSR) often returns expressions that are larger than necessary, with dormant branches and finely tuned algebraic configurations t
- PaperCorrFlow: Self-Correcting Flow Matching
Flow-matching models generate samples through iterative velocity predictions, but typically do not revisit these predictions using the intermediate representations that p
- PaperReTRACE: Feedback-Guided LLM Agent in a Chemistry Harness for Retrosynthesis Planning
Computer-aided retrosynthesis has advanced through single-step prediction, tree search and route scoring, but complex targets still require judgement over the whole route
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.