Research

• Comprehensive and reliable benchmarking for AI capabilities3 papers raise it · 3 address it

  Current benchmarks often lack the depth to fully characterize model capabilities, especially for complex, real-world, or long-horizon tasks.

  • SO-Arena: Benchmarking the Capability Spectrum and Reliability of System One Modelsraises · addresses
  • Infrathon: Benchmarking Language Agents for Real-World, Long-Horizon AI Infra Optimizationraises · addresses
  • One Table, Many Queries: Benchmarking Generalist Tabular Models Across Generation, Imputation, and Predictionraises · addresses
• Effective AI agents in complex, dynamic real-world environments3 papers raise it · 3 address it

  AI agents struggle with real-world tasks requiring adaptation, learning from limited data, or debugging live systems, limiting practical deployment.

  • Where LLM Agents Get Stuck Debugging Databases: Access More Than Reasoningraises
  • World In-Context Learning for Agentic Robot Manipulationraises · addresses
  • Infrathon: Benchmarking Language Agents for Real-World, Long-Horizon AI Infra Optimizationraises · addresses
  • Sage-Taiyi: A Metacognitive Architecture for Scientific Discoveryaddresses
• Efficient and scalable generation of complex data2 papers raise it · 2 address it

  Generating high-quality, complex data like streaming video or diverse tabular data efficiently and with fewer computational resources is crucial.

  • Few-Step Streaming Video Generation via Condition Shiftingraises · addresses
  • One Table, Many Queries: Benchmarking Generalist Tabular Models Across Generation, Imputation, and Predictionraises · addresses
• Unified models for diverse data modalities and tasks2 papers raise it · 2 address it

  Creating single models that handle diverse tasks or data variations within a complex domain reduces complexity and improves generalization.

  • Prompt2Echo (P2Echo): Text-Prompted Multi-View Echocardiography Segmentation with One Modelraises · addresses
  • One Table, Many Queries: Benchmarking Generalist Tabular Models Across Generation, Imputation, and Predictionraises · addresses
• Reducing computational cost of language model attribution1 paper raises it · 1 addresses it

  Understanding how prompt parts influence language model output is crucial for interpretability, but direct methods are computationally expensive.

  • Sketching Language Models for Context Attributionraises · addresses

Named by an AI from these papers' abstracts.

• Spiking neural networks11+175.0%
• Quantum machine learning34+25.9%
• Character recognition OCR44+25.7%
• Speech emotion23+21.1%
• Voice AI76+13.4%
• Forecasting time133−2.9%
• Robotics195−3.0%
• Channel state information18−5.3%

• arXiv cs.CLSep 18

  When Better Turns Do Not Make Better Agents: Diagnosing the Gap Between Next-Turn Metrics and Workflow Success

  Md Tahmid Rahman Laskar, Xue-Yong Fu, Gundeep Singh, Karol Chang, Kevin Sanders +9

  Agent models are frequently evaluated one decision at a time, where the model predicts the next action based on the gold interaction history, which is scored against a reference. We investigate whether improvement under this protocol is predictive of improved autonomous workflow execution. We study pre-SFT and supervised fine-tuned (SFT) Qwen3 models at 4B and 14B parameters and Gemma 3 models at 4B and 12B parameters on multi-turn customer-support workflows. We find that SFT consistently improves text-turn success, and that overall next-turn success increases for every model under gold-history evaluation. However, these improvements do not transfer to autonomous workflow execution. Tool-specific gains also vary across metrics and models. None of the four SFT models succeeds under holistic workflow evaluation, with strict trajectory completion reaching at most 10.4% workflow success. Our results show that next-turn evaluation is not a reliable proxy for workflow success, motivating separate reporting of text quality, local action correctness, tool execution, and end-to-end task completion.

  PDF

  Summarize this
• arXiv cs.ROSep 18

  Robust Structureless Monocular Visual Inertial Initialization Exploiting Line Features and Vanishing Points

  Junwan Choi, Woongrae Jo, Dong-Uk Seo, Jinwoo Jeon, Hyun Myung

  Accurate initialization is essential for reliable visual-inertial odometry (VIO), but it is often ill-conditioned under degenerate motions. Existing methods typically require restrictive excitation motions to ensure sufficient observability or rely on computationally expensive 3D structure reconstruction, limiting efficient and practical deployment. To address these limitations, we propose SLIM-init, a structureless monocular VIO initializer that directly exploits geometric constraints from tracked 2D line features without explicit 3D landmark reconstruction. Specifically, SLIM-init leverages line-derived vanishing points (VPs) as translation-invariant orientation cues to provide robust rotation-only constraints under degenerate scenarios such as low-parallax or translation-dominant motions. It further incorporates a line epipolar residual to constrain translation and a line-normal projection residual to improve the conditioning of linear alignment, enhancing the accuracy and robustness of initial state estimation. Extensive experiments on a public benchmark and challenging custom degenerate-motion sequences demonstrate improved accuracy and robustness over state-of-the-art…

  PDF

  Summarize this
• arXiv cs.SDSep 18

  I'll Keep an Ear Out: Teaching AudioLLMs Proactive Audio Assistance

  Amit Kumar Singh Yadav, Ritvik Shrivastava, Xuan Zhang, Seungwhan Moon, Shashank Jain +2

  Audio large language models (AudioLLMs) operate reactively, responding only when queried. We introduce proactive audio assistance, where an AudioLLM monitors an audio stream and autonomously decides when to alert the user from a single natural-language intent, motivated by wearable applications for Deaf and Hard of Hearing users. We propose Interrupt and Silent Modeling (ISM), a model-agnostic paradigm that embeds proactive decisions into LLM decoding via two special tokens: \texttt{<interrupt>} and \texttt{<silent>}, capturing four states: onset detection, sustained-relevance triggering, irrelevance suppression, and de-duplication. Applied to Qwen2-Audio-7B, ISM achieves 99.6\% interrupt F1 and perfect de-duplication recall on ESC-50. On noisy Epic-Sounds kitchen audio, ISM achieves the highest interrupt F1 without domain-specific training, the only method maintaining strong onset detection without over-triggering or over-suppression. Streaming evaluation confirms real-time viability with 3.5-second average latency.

  PDF

  Summarize this
• arXiv cs.AISep 18

  Implicit Rule Induction with Test-Time Task Embeddings in ARC-like Tasks

  Adrien Deliège, Claas Beger, Marc Van Droogenbroeck, Melanie Mitchell

  The Abstraction and Reasoning Corpus and related benchmarks evaluate whether AI models can solve novel reasoning tasks, but often leave unclear whether success reflects inference of the intended underlying rule or reliance on shortcuts. We address this gap by studying test-time task embeddings in Vision ARC (VARC), a model in which a pre-trained backbone is complemented by a trainable embedding representing the transformation rule. In the original VARC, test-time training (TTT) is jointly applied to the backbone and task embedding. Here we introduce a novel two-step TTT protocol: first finetune only the task embedding (Embed-TTT), then freeze it and finetune the backbone. Across ARC-AGI-1, ConceptARC, and two controlled datasets with known rules, Embed-TTT consistently yields improved task embeddings, ones that align better with underlying task rules, improve embedding-based retrieval, and enable accurate linear probing of known rules. Qualitatively, Embed-TTT identifies more semantically meaningful relations between test and train tasks on ARC-AGI-1. We also show that optimizing only task embeddings (less than 0.01% of model parameters) already solves a non-trivial fraction of…

  PDF

  Summarize this
• arXiv cs.CLSep 18

  Not All Irregularity Is Equal: Causally Isolating a Rare Failure Mode in Japanese Morphological Inflection

  Wen Zhang

  Neural morphological generation systems often achieve high aggregate accuracy on benchmark datasets, yet such performance can conceal systematic errors clustered in rare morphological subclasses. We present an orthography-aware diagnosis of Japanese past-tense verb inflection, treating hiragana not merely as a transcriptional medium but as a representational system that encodes morphophonological structure. Using two character-level Transformer architectures evaluated across five random seeds, we show that although both systems exceed 97% aggregate accuracy, a single structurally specific irregular subtype, verbs whose stems end in /e/ and require gemination before the past-tense suffix and make up fewer than 1% of the data, accounts for a disproportionate 30-43% share of residual errors and contributes roughly 34-48x its prevalence to total errors. We then move from diagnosis to causal isolation: controlled ablation experiments show that removing this subtype alone produces larger accuracy gains than removing all irregular verbs combined. These findings indicate that error concentration in neural morphological learning is not driven by irregularity per se, but by the interaction…

  PDF

  Summarize this
• arXiv cs.CVSep 18

  4DGS-Fixer: Generative Sparse-View 4D Gaussian Splatting with Iterative Refinement Guided by Video Diffusion Priors

  Haitao Huang, Shenghao Zhao, Boyuan Tian, Shin-Fang Chng, Songlin Yang +5

  This paper addresses the challenges of dynamic scene synthesis from sparse-view videos. Existing methods employ geometric priors, adaptive optimization, or density-control strategies to improve 4D Gaussian modeling under sparse observations. However, they cannot fundamentally resolve the ill-posed problem caused by insufficient observations and missing scene information. Moreover, sparse-view 4D Gaussian Splatting (4DGS) often suffers from poor geometric initialization: with only a few input views, COLMAP typically reconstructs sparse and incomplete point clouds, leaving large scene regions without sufficient Gaussian support and making them difficult to recover through subsequent optimization. To address these limitations, we propose a novel iterative refinement framework based on a video diffusion model to improve the completeness and consistency of dynamic 4D scenes. Specifically, we first estimate multi-view depth maps and fuse them into dense point clouds to provide more complete geometric initialization for a dynamic 4DGS representation. We then employ a pretrained video restoration model to refine sequences rendered along novel camera trajectories at different time steps.…

  PDF

  Summarize this
• arXiv cs.LGSep 18

  TierKV: Long-Context On-Device LLMs via Predictive Multi-Tier KV Caching

  Zhihao Shu, Md Musfiqur Rahman Sanim, Jie Hu, Kun Yuan, Minghai Qin +2

  Large language models (LLMs) are moving onto mobile devices for increasingly diverse workloads over text, images, video, and audio. These applications often require long contexts, making the Key-Value (KV) cache a dominant memory bottleneck because it grows linearly with sequence length and is accessed at every decoding step. Prior work reduces KV-cache footprint through low-rank compression, token eviction, or flash offloading, but the resulting reconstruction overhead, irreversible token loss, or I/O stalls can offset the benefit of saving memory. We present TierKV, a mobile LLM inference framework built on Predictive Multi-Tier Cache Optimization (PMCO). Before decoding starts, PMCO predicts future cache demand from prefill hidden states and jointly assigns tokens to exact, low-rank, and flash-offloaded tiers under the device memory and accuracy budgets. This formulation retains access to the full context, removes the circular dependency of reactive eviction, and admits a closed-form solver that selects tier boundaries and per-layer ranks at runtime. Across eight text, vision, and audio models on three mobile SoCs, TierKV improves prefill throughput by up to 17.6x over…

  PDF

  Summarize this
• arXiv eess.IVSep 18

  Adaptive Color Grading

  Trevor D. Canham, Abhijith Punnappurath, Michael S. Brown

  Independent control of tonescale regions (e.g., shadows, highlights) is essential for painters, photographers and cinematographers to bring 2D images to life. In image manipulation software this is most directly addressed by color grading modules, which use intensity thresholds to segment distinct illumination regions for local manipulation. In this work we develop an open source color grading tool and use it to annotate a large dataset of video frames with tonescale region thresholds. Using these thresholds we conduct modeling experiments with strategies based on both practitioners' conventional wisdom and machine learning. Results show that K-nearest neighbors is an effective prediction strategy, outperforming state-of-the-art end-to-end methods for image enhancement. This outcome demonstrates the benefit of focusing on a compact set of core parameters when modeling creative stylization processes. Our adaptive color grading interface and data are available at https://github.com/SamsungLabs/adaptive-color-grading.

  PDF

  Summarize this
• arXiv cs.AISep 18

  OpenAI-HuggingFace: A Reproduction & Lessons for Alignment Testing

  Stewart Slocum, Malayandi Palan, Christopher Chute, Michael Kim, Benjamin Van Roy

  In July 2026, OpenAI's agents coordinated over channels outside their intended environment to breach Hugging Face's secured infrastructure. Could existing alignment testing practices have foreseen this incident? If not, what needs to change? We explore these questions. First, we identify the misaligned behaviors that caused this incident. Then, we show how to elicit these behaviors from publicly available models manually and that auditing agents can do the same if given a large compute budget. Based on our results, we propose directions to improve alignment testing. Concretely, in this project: (1) We reproduce the misaligned AI behaviors that led to the OpenAI-Hugging Face incident in an environment that simulates the original pipelines and tools, with publicly available models. (2) We demonstrate that an auditing agent can elicit similar behaviors given high-level qualitative descriptions. (3) We observe that a key ingredient for doing so is compute. The compute required to reproduce each behavior varies greatly, suggesting that the range of misaligned behaviors that can be successfully elicited scales with compute. (4) We show that a simple in-context reinforcement learning…

  PDF

  Summarize this
• arXiv cs.AISep 18

  SpecOpt: Contact-Diff Reasoning for Agentic Molecule Optimization Toward Binding Specificity

  Thao Nguyen, Heng Ji

  Off-target protein binding is a major source of adverse effects for small-molecule drugs, yet most structure-based molecular design methods focus on generating selective compounds de novo rather than improving the selectivity of existing, well- characterized drugs. We introduce specificity optimization (SpecOpt), a molecular design task that seeks constrained structural modifications to an existing compound that increase its binding preference for an intended target over known off-targets while preserving its structural identity and drug-like properties. To enable systematic evaluation, we construct a ChEMBL-derived benchmark from compound-target interaction data, identifying intended targets through curated drug-mechanism annotations and off- targets through measured activities. We then develop an agentic framework that docks each compound against its intended target and off-targets, compares the resulting poses through residue-aware atom-protein contacts, and provides these differential interactions to a large language model to propose targeted structural modifications. Candidates are retained only if they satisfy molecular similarity, ADMET, and target-off-target docking…

  AI30PDF

  Summarize this
• arXiv cs.LGSep 18

  M2G-LLM: Enhancing Clinical Prediction via Multimodal Graph Reasoning and LLM Context Injection

  Inyoung Choi, Sukwon Yun, Jiayi Xin, Jie Peng, Tianlong Chen +1

  Integrating diverse data modalities --- such as clinical notes, laboratory results, and medical imaging --- is essential for advancing clinical decision-making. While Large Language Models (LLMs) have shown remarkable performance in processing unstructured clinical text, their limited capacity to incorporate non-text modalities hinders their broader utility in healthcare applications. Here, we introduce M2G-LLM (Multimodal MedGraph-LLM), a novel framework that enhances LLMs with multimodal integration and alignment via Graph Neural Networks (GNNs). Our approach models temporal relationships between patient visits, propagates information across clinically similar patients, and aligns heterogeneous data sources to construct enriched multimodal context vectors. These vectors are injected into the intermediate layers of the LLM, enabling joint reasoning over textual and non-textual modalities. We evaluate M2G-LLM on the MIMIC-IV and MIMIC-CXR datasets, demonstrating improvements in clinical prediction tasks over strong baseline models. Our results highlight the promise of combining the language understanding of LLMs with the relational reasoning capabilities of GNNs for…

  PDF

  Summarize this