model releases

Qiskit QuantumKatas: Adapting Microsoft's Quantum Computing exercises for LLM evaluation

arXiv:2605.27210v1 Announce Type: cross Abstract: We adapt Microsoft's QuantumKatas -- a well-established quantum computing curriculum -- from Q# to Qiskit, the most widely-adopted quantum computing f

Model Releases

Query Symbolically or Retrieve Semantically? A Dataset and Method for Semi-Structured Question Answering

DGX agent

arXiv:2605.27164v1 Announce Type: new Abstract: Retrieval-Augmented Generation (RAG) systems for question answering typically retrieve evidence by semantic similarity between the query and document ch

model-releasesarxiv-cs-ai

27 May 2026

🚀🚀 Qwen3.7-Max just hit #4 on Code Arena, on par with Claude Opus 4.6 ，top-ranked Chinese lab on the board! @arena More to ship. Stay tune…

🚀🚀 Qwen3.7-Max just hit #4 on Code Arena, on par with Claude Opus 4.6 ，top-ranked Chinese lab on the board! @arena More to ship. Stay tuned. 🕶️ Qwen3.7 Max (20250517) debuts at #4 in Code Arena: Front

model-releasesqwen--x

RCSP: Risk-Sensitive Conjectural Scenario Planning for Safe Dynamic Robot Navigation

model-releasesarxiv-cs-ro

arXiv:2605.26348v1 Announce Type: new Abstract: Mobile robots can fail before they collide: a velocity that is safe now may commit the robot to a passage that moving obstacles will soon close. We stud

Reasoning, Code, or Both? How Large Language Models Handle Variations in Math Questions

arXiv:2605.26414v1 Announce Type: new Abstract: Large Language Models (LLMs) achieve impressive accuracy on mathematical reasoning benchmarks, yet their performance drops when problems are modified wi

Receipt Replay OOD: A Small Benchmark for Screen Replay Detection Under Domain Shift

arXiv:2605.26855v1 Announce Type: new Abstract: Public datasets such as DLC-2021, SynID, and KID34K have significantly contributed to research on presentation attack detection for identity documents,

Reliable Extraction of Clinical Follow-Up Instructions: A Hybrid Neural-Symbolic Pipeline

arXiv:2605.26560v1 Announce Type: cross Abstract: Objective. Outpatient notes carry follow-up instructions pairing actions with future times ('MRI brain in two weeks'). Extracting (action, date) pairs

ReMoE: Boosting Expert Reuse through Router Fine-Tuning in Memory-Constrained MoE LLM Inference

arXiv:2605.27081v1 Announce Type: cross Abstract: Fine-grained Mixture-of-Experts (MoE) models sparsely activate only a subset of experts per token, reducing activated computation while maintaining hi

Representation-Aware Unlearning via Activation Signatures: From Suppression to Entity-Signature Erasure

arXiv:2601.10566v5 Announce Type: replace Abstract: Entity-level unlearning is usually evaluated by what a model says: whether it stops naming the target, refuses a query, or shifts a Truth Ratio dist

Resolving Ambiguity in Composed Image Retrieval via Calibrated Interaction

arXiv:2605.24634v2 Announce Type: replace Abstract: Composed image retrieval (CIR) searches a corpus with a reference image and a text describing how to modify it. Despite rapid progress from triplet-

Rethinking the Multilingual Reasoning Gap with Layer Swap

arXiv:2605.26735v1 Announce Type: new Abstract: Recent reasoning Large Language Models produce a chain-of-thought (CoT) predominantly in English, even when prompted in non-English languages. Prior wor

Risk Averse Alert Prioritization for IDS Using Subnormal Gaussian Fuzzy Models

arXiv:2605.27299v1 Announce Type: cross Abstract: Modern intrusion detection systems generate thousands of alerts daily, but alert fatigue severely limits security operations effectiveness due to too

RLVR Datasets and Where to Find Them: Tracing Data Lineage for Better Training Data

arXiv:2605.26971v1 Announce Type: new Abstract: The proliferation of Reinforcement Learning from Verifiable Rewards (RLVR) datasets has exacerbated provenance collapse due to unclear lineage among exi

RoadGIE: Towards A Global-Scale Aerial Benchmark for Generalizable Interactive Road Extraction

arXiv:2605.26862v1 Announce Type: new Abstract: Accurate road segmentation from aerial imagery is fundamental to many geospatial applications. However, existing datasets often suffer from limited scen

Scaling, Benchmarking, and Reasoning of Vision-Language Agents for Mobile GUI Navigation

arXiv:2605.27134v1 Announce Type: new Abstract: Vision-Language Models (VLMs) have shown rapid progress in mobile GUI navigation. This paper presents a systematic study of data scaling, benchmarking,

Scaling GraphLLM with Bilevel-Optimized Sparse Querying

arXiv:2602.09038v2 Announce Type: replace-cross Abstract: LLMs have recently shown strong potential in enhancing node-level tasks on text-attributed graphs (TAGs) by providing explanation features. Ho

Scheduled Style Injection: Expanding the Style-Content Pareto Frontier in Training-Free Diffusion-based Style Transfer

arXiv:2605.26538v1 Announce Type: new Abstract: Style transfer with pre-trained diffusion models has advanced rapidly, but a core question remains underexplored: where in the model should style inject

ScientistOne: Towards Human-Level Autonomous Research via Chain-of-Evidence

arXiv:2605.26340v1 Announce Type: new Abstract: Autonomous research agents produce competitive solutions and professional-looking manuscripts, yet their outputs contain verifiability failures undetect

SEAL: Self-Evolving Agentic Learning for Conversational Question Answering over Knowledge Graphs

arXiv:2512.04868v2 Announce Type: replace-cross Abstract: Knowledge-based conversational question answering (KBCQA) confronts persistent challenges in resolving coreference, modeling contextual depend

SEC-bench Pro: Can Language Models Solve Long-Horizon Software Security Tasks?

arXiv:2605.26548v1 Announce Type: cross Abstract: Large language models (LLMs) now support automated software security tasks, including vulnerability discovery and proof-of-concept (PoC) generation. E

SeDT: Sentence-Transformer Decision-Transformer Conditioning for Multi-Turn Conversation Reliability

arXiv:2605.26788v1 Announce Type: cross Abstract: Large language models (LLMs) achieve impressive performance when a task is fully specified in a single turn, yet the same models lose up to 39% of tha

Seeing vs. Believing: Evaluating the Language Bias of Open-Source MLLMs in Counter-Intuitive Scenes

arXiv:2601.07737v2 Announce Type: replace-cross Abstract: Multimodal Large Language Models (MLLMs) have demonstrated remarkable performance in mainstream visual understanding tasks, but their ability

Self-Ensembling Vision-Language Models for Chart Data Extraction

arXiv:2605.27298v1 Announce Type: new Abstract: Charts effectively convey quantitative information, but the underlying data are often locked in image form, hindering reuse and analysis. Manually digit

Self-Verified Distillation: Your Language Model Is Secretly Its Own Synthetic Data Pipeline

arXiv:2605.26132v1 Announce Type: new Abstract: Can post-trained large language models (LLMs) further improve themselves using only unlabeled prompts, without external teachers or feedback from tools?

Sentinel: Embodied Cooperative Spatial Reasoning and Planning

arXiv:2605.26239v1 Announce Type: new Abstract: In this work, we study Cooperative Spatial Intelligence, the ability of decentralized embodied agents to coordinate effectively under dynamic environmen

Separating Semantic Competition from Context Length in RAG Reading

arXiv:2605.27294v1 Announce Type: new Abstract: Retrieval-augmented generation (RAG) systems can respond incorrectly even when the correct passage was retrieved. The model must still read the retrieve

Shedding Light on Dark Matter at the LHC with Machine Learning

arXiv:2509.15121v2 Announce Type: replace-cross Abstract: We investigate a WIMP dark matter (DM) candidate in the form of a singlino-dominated lightest supersymmetric particle (LSP) within the Z_3-sym

Shopping Companion: A Memory-Augmented LLM Agent for Real-World E-Commerce Tasks

arXiv:2603.14864v2 Announce Type: replace Abstract: In e-commerce, LLM agents show promise for shopping tasks such as recommendations, budget management, and bundle deals, where accurately capturing u

SilIF: Silhouette-Augmented Isolation Forest for Unsupervised Transaction Fraud Detection

arXiv:2605.26135v1 Announce Type: new Abstract: Unsupervised anomaly detection is widely used in transaction fraud detection where labels are scarce. Isolation Forest (IF) is among the most popular cl

SOLE-R1: Video-Language Reasoning as the Sole Reward for On-Robot Reinforcement Learning

arXiv:2603.28730v2 Announce Type: replace-cross Abstract: Vision-language models (VLMs) have shown impressive capabilities across diverse tasks, motivating efforts to leverage these models to supervis

Someone just asked me “What I don’t get is why you see it as some kind of failure that AI labs are now using harnesses and neurosymbolic too…

model-releasesgary-marcus--x

Someone just asked me “What I don’t get is why you see it as some kind of failure that AI labs are now using harnesses and neurosymbolic tools…?” I don’t! As I argued in my newsletter on Claude Code (

SONAR-LLM: Autoregressive Transformer that Thinks in Sentence Embeddings and Speaks in Tokens

arXiv:2508.05305v2 Announce Type: replace Abstract: The recently proposed Large Concept Model (LCM) generates text by predicting a sequence of sentence-level embeddings and training with either mean-s

SpaceVista: All-Scale Visual Spatial Reasoning from mm to km

arXiv:2510.09606v2 Announce Type: replace Abstract: With the current surge in spatial reasoning explorations, researchers have made significant progress in understanding indoor scenes, but still strug

SpatialBench: Is Your Spatial Foundation Model an All-Round Player?

arXiv:2605.27367v1 Announce Type: new Abstract: While spatial foundation models have demonstrated impressive performance on standard datasets, a critical question remains: are they truly all-round pla

Stability Implies Redundancy: Delta Attention Selective Halting for Efficient Long-Context Prefilling

arXiv:2604.18103v2 Announce Type: replace Abstract: Prefilling computational costs pose a significant bottleneck for Large Language Models (LLMs) and Large Multimodal Models (LMMs) in long-context set

SteelDS: A High-Resolution Video Dataset of E40 Steel Scrap for Object Detection and Instance Segmentation

arXiv:2605.26682v1 Announce Type: cross Abstract: This dataset provides high-resolution, annotated video sequences of shredded E40-grade steel and copper scrap on a conveyor belt. Captured in a contro

Stochastic global optimization of continuous functions via random walks on Grassmannians

arXiv:2605.14151v1 Announce Type: cross Abstract: We introduce a stochastic global optimization method based on random walks on Grassmannian manifolds. To minimize a continuous objective ell:R^drighta

Strategies for Guiding LLMs to Use Software Design Patterns: A Case of Singleton

arXiv:2605.26898v1 Announce Type: cross Abstract: Large Language Models (LLMs) can generate functional source code from natural-language prompts, but often fail to consistently follow higher-level arc

Stronger models do not always need lighter harnesses. Everyone believes more structured harnesses universally improve reliability, and that …

Stronger models do not always need lighter harnesses. Everyone believes more structured harnesses universally improve reliability, and that higher-capability models need proportionally less structural

model-releasesdair-ai--x

Structured Relational Reasoning for Group Activity Assessment

arXiv:2508.07996v2 Announce Type: replace Abstract: Group Activity Detection (GAD) involves recognizing social groups and their collective behaviors in videos. Vision Foundation Models (VFMs), like DI

SWE-Adept: An LLM-Based Agentic Framework for Deep Codebase Analysis and Structured Issue Resolution

arXiv:2603.01327v2 Announce Type: replace-cross Abstract: Large language models (LLMs) exhibit strong performance on self-contained programming tasks. However, they still struggle with repository-leve

TADDLE: A Tool-Augmented Agent for Detecting Deficient LLM-Generated Peer Reviews

arXiv:2605.26911v1 Announce Type: new Abstract: LLM-generated peer reviews are increasingly common at major venues, yet their deficiencies are hard to detect because they are uniformly fluent and well

Temporal Simultaneity Predicts Annotation Quality in Sentiment Corpora

arXiv:2605.27239v1 Announce Type: new Abstract: Annotation quality is difficult to sustain when campaigns span weeks or months with small annotator pools. We present a Setswana sentiment dataset of 3,

The Bridge-Garden Dilemma in LLM Distillation: Why Mixing Hard and Soft Labels Works

arXiv:2605.26246v1 Announce Type: new Abstract: Knowledge distillation (KD) transfers knowledge from a large teacher model to a smaller student. In language modeling, the student is trained either on

The Compressive Knowledge Graph Hypothesis: Which Graph Facts Matter for Scientific Hypothesis Generation?

arXiv:2605.27176v1 Announce Type: new Abstract: Knowledge graphs (KGs) can provide structured scientific context to language models, but it remains unclear which graph facts actually shape the generat

The MiniMax M2 series was one of the most widely used open-weight LLM series earlier this year. Now, we got a technical report with some int…

model-releasessebastian-raschka--x

The MiniMax M2 series was one of the most widely used open-weight LLM series earlier this year. Now, we got a technical report with some interesting tidbits. I summarized some of them below: 1. Full a

The Stability of Singular Distribution: A Spectral Perspective on the Two-Phase Dynamics of Language Model Pre-training

arXiv:2605.26489v1 Announce Type: new Abstract: Large language model pre-training typically exhibits a two-phase trajectory: a fast initial loss drop followed by a prolonged slow improvement. We ident

Timestep-Aware SVDQuant-GPTQ for W4A4 Quantization of Wan2.2-I2V

arXiv:2605.27003v1 Announce Type: cross Abstract: W4A4 quantization of large video diffusion Transformers offers substantial memory savings but is hindered by two main challenges: sparse large-magnitu