research

Small RL Controller, Large Language Model: RL-Guided Adaptive Sampling for Test-Time Scaling

arXiv:2606.03102v1 Announce Type: new Abstract: Test-time scaling improves the reasoning performance of large language models but incurs substantial cost in both total computation and latency. Existin

Research

Social Caption: Evaluating Social Understanding in Multimodal Models

DGX agent

arXiv:2601.14569v2 Announce Type: replace Abstract: Social understanding abilities are crucial for multimodal large language models (MLLMs) to interpret human social interactions. We introduce SOCIAL

researcharxiv-cs-cl

3 Jun 2026

SparseStreet: Sparse Gaussian Splatting for Real-Time Street Scene Simulation

arXiv:2606.03909v1 Announce Type: new Abstract: While 3D Gaussian Splatting has shown promising results in street scene reconstruction, existing methods require massive numbers of Gaussian primitives

Spectral-Progressive Thought Flow for Lightweight Multimodal Reasoning

arXiv:2606.02842v1 Announce Type: new Abstract: Multimodal spatial reasoning often relies on long chains of intermediate textual and visual thoughts, where accumulating visual tokens and dense cross-m

Speech Emotion Recognition using Attention-based LSTM-Network with Residual Connection

arXiv:2606.03359v1 Announce Type: cross Abstract: Speech emotion recognition is an important component of modern human-computer interaction systems. However, many state-of-the-art approaches rely on l

Static and Dynamic Representations for Tactile Contact-Angle Estimation with Event-Based Sensors

arXiv:2606.03545v1 Announce Type: new Abstract: Event-based tactile sensing offers low-latency signal acquisition for contact-rich robotic interaction. This paper investigates contact-angle estimation

researcharxiv-cs-ro

Structure-Guided Mixed Masked Pretraining and Spatial Continuity Regularization for Printed Circuit Board Defect Detection

arXiv:2606.03508v1 Announce Type: new Abstract: Printed circuit board (PCB) defect detection is an essential part of automated optical inspection (AOI); yet it remains challenging in practice because

Structures Facilitate Retrieve, Rerank, and Generate

arXiv:2606.03247v1 Announce Type: new Abstract: Document-grounded dialogue systems (DGDS) utilize knowledge from external documents to answer domain-specific user questions. Existing solutions typical

Suboptimality bounds for trace-bounded SDPs enable a faster and scalable low-rank SDP solver SDPLR+

arXiv:2406.10407v3 Announce Type: replace-cross Abstract: Semidefinite programs (SDPs) and their solvers are powerful tools with many applications in machine learning and data science. Designing scala

Target Updates May Stabilize Linear Q-Learning: Periodic and Soft Dynamics

arXiv:2606.02645v1 Announce Type: cross Abstract: Periodic target updates in Q-learning and soft target updates in actor-critic methods are empirically well established stabilization mechanisms, but t

Template Collapse and Information-Theoretic Limits in Camera rPPG Pulse Morphology Restoration

arXiv:2606.03802v1 Announce Type: new Abstract: Objective: Consumer face camera remote photoplethysmography (rPPG) enables passive cardiovascular monitoring, but whether single-cycle waveform morpholo

Terminal Time and Angle-Constrained Nonlinear Intercept Guidance

arXiv:2606.02872v1 Announce Type: cross Abstract: This paper considers the problem of simultaneously controlling an interceptor's impact time and impact angle using its lateral acceleration as the sol

researcharxiv-cs-ro

Test-Time Optimization of Physical Query Plans with LLMs

arXiv:2602.10387v2 Announce Type: replace-cross Abstract: Traditional query optimization relies on cost-based optimizers that estimate execution cost (e.g., runtime, memory, and I/O) using predefined

Testing Most Influential Sets

arXiv:2510.20372v4 Announce Type: replace-cross Abstract: Small influential data subsets can dramatically impact model conclusions, with a few data points overturning key findings. While recent work i

Testing the Test: Score-Direction Instability in Class-Split Anomaly Detection

arXiv:2606.02601v1 Announce Type: new Abstract: Within-dataset class-split evaluation is widely used as a proxy for fully unconditional out-of-distribution anomaly detection. We show that this protoco

Text-attributed Graph Condensation via Text Selection and Attribute Matching

arXiv:2606.03839v1 Announce Type: new Abstract: Text-Attributed Graph (TAG) is an important type of graph structured data, where each node has a text description. TAG models usually train a Graph Neur

The Download: Trump’s new AI order, and smart glasses for warfare

This is today’s edition of The Download, our weekday newsletter that provides a daily dose of what’s going on in the world of technology. 5 key points in Trump’s new AI order Less than two weeks after

researchmit-tech-review

The Efficiency vs. Accuracy Trade-off: Optimizing RAG-Enhanced LLM Recommender Systems Using Multi-Head Early Exit

arXiv:2501.02173v2 Announce Type: replace-cross Abstract: The deployment of Large Language Models (LLMs) in recommender systems for predicting Click-Through Rates (CTR) necessitates a delicate balance

The Hermes Web Dashboard got a major overhaul: it is now a feature-complete admin panel that you can manage entirely from your browser.

The Hermes Web Dashboard has been significantly redesigned to function as a comprehensive admin panel with full feature parity, allowing users to manage all operations directly through a web browser i

researchnous-research--x

The Impact of Temporal Granularity on Socio-Demographic Inference from Household Load Profiles

arXiv:2606.03358v1 Announce Type: new Abstract: Smart meter data can reveal sensitive socio-demographic characteristics of households, raising privacy concerns. While this risk has been demonstrated a

The next chapter in flood resilience: Open sourcing Google’s hydrology framework

Google has open-sourced its flood forecasting framework, which replicates operational FloodHub model training settings and reflects methodology described in a 2024 Nature paper for global ungauged flo

researchgoogle-research

The Shape of Addition: Geometric Structures of Arithmetic in Large Language Models

arXiv:2606.03645v1 Announce Type: cross Abstract: Large Language Models exhibit paradoxical fragility in fundamental arithmetic, implying a disconnect between internal computation and discrete output.

The Unsampled Truth: Psychometrics in SLMs Measure Prompt Artifacts, Not Psychological Constructs

arXiv:2606.03357v1 Announce Type: cross Abstract: When prompting SLMs for psychometric assessments, researchers assume the outputs reflect semantic reasoning. We evaluate this premise across 13 open-w

Theoretical Aspects of Lie Groupoid and Lie Algebroid Equivariant Convolutional Neural Networks

arXiv:2606.02758v1 Announce Type: cross Abstract: We introduce Lie groupoid equivariant neural networks as a specialization of recently proposed topological category-equivariant neural networks to the

Thinking Past the Answer: Evaluating Harmful Overthinking in Large Reasoning Models

arXiv:2606.02835v1 Announce Type: new Abstract: Large Reasoning Models (LRMs) improve performance by generating explicit intermediate reasoning traces through increased test-time compute, yet the assu

this is an interesting point in the new ted chiang piece – no one really claims that alphafold is conscious, or that sora or midjourney or d…

Yann LeCun discusses a point from a Ted Chiang piece about the lack of claims regarding consciousness in recent AI systems like AlphaFold, Sora, and Midjourney, suggesting skepticism about attributing

researchyann-lecun--x

TIDFormer: Exploiting Temporal and Interactive Dynamics Makes A Great Dynamic Graph Transformer

arXiv:2506.00431v2 Announce Type: replace Abstract: Due to the proficiency of self-attention mechanisms (SAMs) in capturing dependencies in sequence modeling, several existing dynamic graph neural net

TimeOmni-VL: Unified Models for Time Series Understanding and Generation

arXiv:2602.17149v2 Announce Type: replace-cross Abstract: Recent time series modeling faces a sharp divide between numerical generation and semantic understanding, with research showing that generatio

Tonal parsimony in chord-sequence analysis: combining modulation cost and tonal vocabulary

arXiv:2606.03459v1 Announce Type: cross Abstract: We study the assignment of local tonalities to chord sequences, a task useful for harmonic analysis, composition, and jazz-oriented improvisation. Sta

Towards Non-Monotonic Entailment in Propositional Defeasible Standpoint Logic

arXiv:2606.03655v1 Announce Type: new Abstract: Recent work in defeasible reasoning has seen notions of preferential semantics and entailment in the style of Kraus et al. applied to modal logics. Howe

Tracking Urban Atmospheric Pollutants using Sentinel-5P Satellite Data

arXiv:2606.02592v1 Announce Type: cross Abstract: Urban nitrogen dioxide (NO_2) is a key indicator of combustion-related air pollution and exhibits strong spatial and temporal variability in cities. T

TrAction: Action Recognition with Sparse Trajectories

arXiv:2606.03490v1 Announce Type: new Abstract: Modern action recognition models operate on memory- and compute-intensive dense RGB video volumes and frequently exploit appearance and background short

Training a Predictive Coding Network on ImageNet using Equilibrium Propagation

arXiv:2606.03584v1 Announce Type: new Abstract: Equilibrium Propagation (EP) is a physics-based training framework that has primarily been employed in energy-based models, including continuous Hopfiel

Trajectory-Aware Node Contributions and the Limits of Static Controllability

arXiv:2606.03067v1 Announce Type: cross Abstract: A recurring data mining task in complex networks is to determine how individual nodes contribute to system behavior. Existing approaches rely on eithe

Trans GAN-WT: A Feature Extraction and Interactive Learning-Based Anomaly Detection Model for Wind Turbine Time Series Data

arXiv:2606.03112v1 Announce Type: cross Abstract: With the increasing scale and number of wind farms, wind turbines' daily operation and maintenance costs are increasing. To reduce operation and maint

Translating Classical Poetry into Modern Prose

arXiv:2606.02806v1 Announce Type: new Abstract: We introduce Padyam2Gadyam, a dataset for the task of poem-to-prose translation from 13th-17th Century Telugu Classical Poetry to contemporary Telugu an

TreeFlash: Parallel AR-Approximation for Faster Speculative Decoding

arXiv:2606.03819v1 Announce Type: new Abstract: One-shot block drafters for speculative decoding generate the full draft in a single forward pass, achieving strong throughput by eliminating sequential

Two-Action Apple Tasting with Switching Costs

arXiv:2606.03851v1 Announce Type: new Abstract: We study the two-action apple-tasting problem with switching costs against an oblivious adversary. In an equivalent normalized formulation, at each roun

Typhoon: Towards an Effective Task-Specific Masking Strategy for Pre-trained Language Models

arXiv:2303.15619v2 Announce Type: replace-cross Abstract: The choice of which tokens to mask is a central, under-examined design decision in masked language modeling (MLM). Standard pretraining masks

Unveiling the Structure of Do-Calculus Reasoning via Derivation Graphs

arXiv:2606.03719v1 Announce Type: new Abstract: The do-calculus defines a general system of inference for interventional queries, allowing causal quantities to be transformed through successive applic

Value-Aware Stochastic KV Cache Eviction for Reasoning Models

arXiv:2606.03928v1 Announce Type: cross Abstract: Reasoning models improve accuracy through extended chains of thought, but their long outputs create a memory and compute bottleneck. KV cache eviction

Wavelet as Tokenizer: Preliminary Results on a Shared Wavelet Token Schema for Natural Signals

arXiv:2606.02631v1 Announce Type: cross Abstract: This paper studies whether audio, images, and video can share a common wavelet token schema rather than relying on separate modality-specific latent g

Weak Diffusion Priors Can Still Achieve Strong Inverse-Problem Performance

arXiv:2601.22443v2 Announce Type: replace-cross Abstract: Can a diffusion model trained on bedrooms recover human faces? Diffusion models are widely used as priors for inverse problems, but standard a

When Does Complexity Conditioning Help a Frozen Sentence Embedding? A Controlled Study of Per-Sentence and Pair-Level Difficulty Adaptation

arXiv:2606.03244v1 Announce Type: new Abstract: A common intuition is that sentence embeddings should adapt to the difficulty of the input. We test this intuition in a controlled, multi-seed setting:

When Should LLMs Be Less Specific? Selective Abstraction for Reliable Long-Form Text Generation

arXiv:2602.11908v3 Announce Type: replace Abstract: LLMs are widely used, yet they remain prone to factual errors that erode user trust and limit adoption in high-risk settings. One approach to mitiga

Why Are Linear RNNs More Parallelizable?

arXiv:2603.03612v3 Announce Type: replace-cross Abstract: The community is increasingly exploring linear RNNs (LRNNs) as language models, motivated by their expressive power and parallelizability. Whi

Worth Remembering: Surprise-Gated Robot Episodic Memory

arXiv:2606.03787v1 Announce Type: new Abstract: Robots solving generalist tasks need to be able to ground instructions in their past experience, since humans may refer to notable past events when givi

researcharxiv-cs-ro

X-RAY: Mapping LLM Reasoning Capability via Formalized and Calibrated Probes

arXiv:2603.05290v2 Announce Type: replace Abstract: Large language models (LLMs) achieve promising performance, yet their ability to reason remains poorly understood. Existing evaluations largely emph