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
- PaperReconstruction of Unobserved Core Electron Density in Tokamak Plasmas with a Neural Operator Transport Surrogate and Uncertainty Quantification
Real-time control of tokamak plasmas requires the electron density profile. However, in a reactor-relevant device, diagnostic port access is limited and the profile can b
- PaperMOMO: Human Motion from Moving Sounds
Human responses to sound depend not only on its semantic content, but also on the evolving spatial relationship between source and listener, conveyed through spatial audi
- PaperComparing Sparsified MLPs and Transcoders: Many Transcoder Features Are Neurons in Disguise
MLP neurons in transformer language models are widely understood to be polysemantic, motivating transcoders - sparse, learned approximations of MLP layers - as interpreta
- PaperHABIT-Bench: Evaluating Habit Induction from Longitudinal Weak Evidence in Agent Memory
In long-term interactions with large language model (LLM) agents, users reveal habits through their choices and actions. These habits capture implicit user information th
- PaperAxiomatic World Modeling for Physics Reasoning
Recent research-level physics-reasoning benchmarks for LLMs reveal a failure mode that lies not in knowledge or execution, but in modeling the world being reasoned about.
- PaperEnhancing analytical photon transport in turbid media through physics-guided neural network corrections
Analytical methods provide rapid and computationally efficient predictions of light transport in turbid media, making them attractive for real-time and inverse applicatio
- Paper$M^2Net$: Unifying Scale-Specific Structures and Prototype Decomposition for Spatial-Temporal Forecasting
Spatial-temporal forecasting is pivotal for intelligent urban management yet remains challenging due to the intricate coupling of spatial dynamics and temporal non-statio
- PaperProbePO: Sparse Probes, Redistributed Credit for Critic-Free LLM Reinforcement Learning
Reinforcement learning from verifiable rewards assigns one terminal reward to an entire reasoning trajectory, obscuring how individual reasoning steps contributed to the
- PaperTopoCompile: Molecular Generation with Exact Global Count Constraints
Molecular generation designs novel molecules with desired structures and properties. Global count constraints specify molecular size, elemental composition, and ring cont
- PaperWhat "Form'' of Uncertainty Does Conformal Prediction Quantify?
Conformal prediction (CP) is a post-hoc calibration method that returns prediction sets with distribution-free coverage guarantees, and the size of the output set is ofte
- PaperDenoising Implicit Variational Inference
Semi-implicit variational inference (SIVI) expands the representational capacity of variational families, but optimizing the Evidence Lower Bound (ELBO) remains challengi
- PaperBEM: Learning Bregman Divergences for Concept Erasure in Flow Matching Models
Concept erasure removes harmful, private, or copyrighted concepts from text-to-image models while preserving their other abilities. Leading models such as FLUX and Stable
- PaperGazeAct: A Human-Gaze-Annotated Manipulation Dataset for Attention-Regularized Policies
Vision-language-action (VLA) policies must ground language instructions in the right objects, contact points, and target locations for reliable manipulation. Human gaze p
- PaperSAP-Depth: Scene-Adaptive Probability Framework for Self-Supervised Monocular Depth Estimation
Self-supervised monocular depth estimation remains challenging due to the loss of fine-grained details and limited adaptability to varying scene structures. In this paper
- PaperHiPPO Functional Memory: Coordinate-Queryable Attention for Irregular Time Series
Irregular time series require models to answer temporal queries at arbitrary coordinates, yet existing approaches typically retain observation-dependent representations t
- PaperInvestigating Length Bias and Robustness in LVLMs for Multiple-Choice Question Answering
Large Vision-Language Models (LVLMs) demonstrate strong performance on multiple-choice question answering (MCQA), yet their reliability under biased conditions remains un
- PaperTideKV: Delayed KV Eviction via Layer-Wise Chunked Prefill for Memory-Efficient Long-Context LLM Inference
Long-context large language model (LLM) inference is important for modern intelligent applications but remains constrained by peak memory during prompt prefill. Existing
- PaperCoTs remain monitorable when being unfaithful requires computation: Replicating and Extending the Necessity Effect Across Eleven Models
While a LLM's chain of thought (CoT) is a promising approach to interpreting model outputs, prior work shows CoT's content does not always accurately reflect the reasonin
- PaperCodecMotion-OAD: Efficient Online Action Detection with Compressed-Domain Motion
Online action detection (OAD) identifies ongoing actions in streaming videos. Many existing OAD systems combine RGB appearance with optical flow, but dense-flow extractio
- PaperConCI: A Controlled Counterfactual Benchmark for Contextual Integrity in LLMs
Contextual integrity (CI) holds that the appropriateness of sharing personal information depends on the context of the information flow, not on the information alone. How
- PaperBackend-Frontend Converter: Component-Based Conversion of .NET Computational Models to TypeScript
Computational models developed in .NET often need to run locally within web applications. We present Backend--Frontend Converter, an architecture for generating TypeScrip
- PaperVBO-MI: A Differentiable Black-Box Optimization Framework via Variational Mutual Information Estimation
Many real-world tasks require optimizing expensive black-box functions accessible only through noisy evaluations, a setting commonly addressed with Bayesian optimization.
- PaperVocal-Tract Acoustics, Aerodynamics, and Overlap-and-Add Synthesis in DYNARTmo
This paper presents the acoustic and aerodynamic extension of DYNARTmo, a dynamic articulatory model for visualizing and synthesizing speech production. Gestural control
- PaperModeling Discourse Profiles in Climate Misinformation Discourse
Prior work on climate misinformation detection typically classifies individual comments or claims using text alone. This framing overlooks a key property of online climat
- PaperSteerable Pluralistic Policy Alignment from Anonymized Crowd Feedback
Pluralistic alignment requires AI systems to learn from diverse populations whose preferences may reflect heterogeneous or even conflicting objectives, and to personalize
- PaperMedPAO-Assist: Edge-Deployable, Modality-Aware Agentic AI for Radiology Report Structuring
The adoption of Large Language Models for radiology report structuring has been largely dominated by either proprietary cloud-based models or large open models requiring
- PaperWrite Once, Check Many: Reusable Ledgers for Post-Hoc Policy Compliance Auditing of Agent Trajectories
Auditing LLM agents against policies is critical to ensure safety but requires rereading long trajectories once per policy. Can we instead record each trajectory once and
- PaperRiSE: Residual Subspace Expert for Generalizable Text-Centric Image Forgery Localization
As AI-assisted image editing becomes increasingly prevalent, Text-Centric Image Forgery Localization (TFL) is essential for protecting trust in financial and legal record
- PaperBeyond Recall Saturation: Scaling Hard-Negative Reranker Training for Industrial Legal Retrieval
Industrial retrieval systems often improve quality by enlarging embedding candidate pools or adopting complex training pipelines. We show that, under a sufficiently large
- PaperPrivate Evaluation of High-Dimensional Functions
We study differentially private black-box evaluation of arbitrary high-dimensional functions. Given a dataset $S$ and query access to a function $f$---whose sensitivity m
- PaperBen-Misandry: A Bengali Dataset and Late-Fusion Transformer Framework for Detecting Anti-Male Gender Hate
Gender based hate speech research in Bengali has focused almost exclusively on misogyny, leaving anti male hate, or misandry, entirely unstudied for this language and cre
- PaperPluralistic Alignment in Large Language Models: Objectives, Human References, and Preference Representations
Pluralistic alignment aims to represent meaningful variation in human preferences rather than collapse heterogeneous judgments into a single target. Yet existing work oft
- PaperWhich Long Documents Matter? A Controlled Study of Data Selection for Context Extension
Natural long documents are widely used for context extension, but which selection pipelines are effective remains unclear. We conduct a controlled comparison on Qwen2.5-3
- PaperSENTRY: A Streaming Edge Network Trust Engine for Real-Time Audio Deepfake Detection
Real-time voice cloning has enabled large-scale streaming deepfake and vishing attacks, while existing Network Detection and Response (NDR) solutions rely on GPU-based po
- PaperUnifying Amplitude-Phase Coupling and Reliable Endogenous Priors for Low-Light Image Enhancement
Frequency-domain methods have shown strong potential for low-light image enhancement (LLIE) because they can effectively regulate global illumination. However, most exist
- PaperLearning to Compose: Recursive Self-Improvement of Shared Executable Stacks for Zero-Shot Long-Horizon Robot Manipulation
Individually competent robot skills can fail when composed: tools may lack a required capability, completion signals may misrepresent physical progress, and one skill may
- PaperO-SCD++: Replay-Free Online Scene Change Detection via Recursive Evidence Fusion
Online scene change detection requires an agent to detect what has changed in a previously mapped environment while it is still on site, observing from unconstrained view
- PaperMeasuring Empowerment from Offline Data for Intrinsically Motivated Exploration
Large, unlabeled datasets of prior experience have become increasingly available for agentic tasks in domains such as robotics and coding. A common recipe for these tasks
- PaperGenerative Retrieval for Reverse Target Fishing with a Proteome-Scale Benchmark
Reverse target fishing identifies protein targets for a query molecule and is central to drug discovery and repurposing. Discriminative approaches adapted from virtual sc
- PaperTree Plurality Veto: Voting in Few Rounds with Efficient Communication and Low Metric Distortion
We consider the metric distortion framework for voting, where $n$ voters and $m$ candidates are embedded in an unknown metric space. A voting rule selects a candidate usi
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.