arXiv AI
Jun 3
The DeepSpeak-Agentic Dataset
arXiv:2606. 03686v1 Announce Type: new Abstract: We present DeepSpeak-Agentic, a dataset of videos comprising over 37 hours of semi-structured conversations between a human and an embodied AI agent.
Benchmarks and evaluation
Leaderboards, eval harnesses and ablations — the contested business of deciding which model is actually better.
arXiv AI
Jun 3
Hedge-Bench: Benchmarking Agents on Hard, Realistic Tasks Pertaining to Financial Reasoning
arXiv:2606. 03918v1 Announce Type: new Abstract: AI agents can increasingly handle the mechanical tasks of financial analysis: retrieving documents, calculating formulas, updating spreadsheets.
arXiv AI
Jun 3
Learn from Your Mistakes: Tree-like Self-Play for Secure Code LLMs
arXiv:2606. 03489v1 Announce Type: cross Abstract: While Large Language Models (LLMs) excel in code generation, they remain prone to replicating subtle yet critical vulnerabilities endemic to their training data.
arXiv AI
Jun 3
DeskCraft: Benchmarking Desktop Agents on Professional Workflows and Human-in-the-Loop Collaboration
arXiv:2606. 03103v1 Announce Type: new Abstract: Real-world professional desktop workflows in specialized creative and engineering software unfold over long horizons and often require human-in-the-loop coordination, where agents proactively seek necessary information and users provide additional instructions, clarifications, feedback, or corrections as the task progresses.
arXiv AI
Jun 3
CORE: Conflict-Oriented Reasoning for General Multimodal Manipulation Detection
arXiv:2606. 03066v1 Announce Type: new Abstract: The rapid rise of generative AI has made multimodal fake news increasingly realistic and pervasive, posing severe threats to public trust and social stability.
arXiv AI
Jun 3
EvoDrive: Pareto Evolution for Safety-Critical Autonomous Driving via Self-Improving LLM Agents
arXiv:2606. 03678v1 Announce Type: new Abstract: Generating safety-critical scenarios is essential for validating and improving autonomous driving systems, yet it inherently requires maximizing adversariality to expose failures while preserving realism.
arXiv AI
Jun 3
Samudra 2: Scaling Ocean Emulators across Resolutions
arXiv:2606. 02610v1 Announce Type: cross Abstract: Ocean general circulation models (OGCMs) are essential to climate science but computationally expensive, limiting ensemble size and forcing scenarios.
arXiv AI
Jun 3
From Long News to Accurate Forecast: Importance-Aware Fusion and PRM-Guided Reflection for Time Series Forecasting
arXiv:2606. 03097v1 Announce Type: new Abstract: Incorporating news into time series forecasting is appealing because news can reveal abrupt exogenous events that historical values alone cannot recover.
arXiv AI
Jun 3
Cost-Aware Query Routing in RAG: Empirical Analysis of Retrieval Depth Tradeoffs
arXiv:2606. 02581v1 Announce Type: cross Abstract: Retrieval-augmented generation (RAG) faces a fundamental three-way tension: deeper retrieval improves factual grounding but inflates token costs and end-to-end latency.
arXiv AI
Jun 3
Reasoning Structure of Large Language Models
arXiv:2606. 03883v1 Announce Type: new Abstract: Large reasoning models (LRMs) are often evaluated using metrics such as final-answer accuracy or token count.
arXiv AI
Jun 3
GTBench: A Curriculum-Grounded Benchmark for Evaluating LLMs as Mathematical Research Assistants in Graph Theory
arXiv:2606. 03144v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used as self-study assistants in technical disciplines, yet their reliability as mathematical reasoning assistants remains poorly understood.
arXiv Machine Learning
Jun 3
Low-Frequency Shortcuts in Texture-Driven Visual Learning
arXiv:2606. 03493v1 Announce Type: cross Abstract: Neural networks suffer from shortcut learning, where learned features generalize well to the training set but not to in-distribution (ID) or out-of-distribution (OOD) test sets.
arXiv AI
Jun 3
FFR: Forward-Forward Learning for Regression
arXiv:2606. 03927v1 Announce Type: cross Abstract: The Forward-Forward (FF) algorithm offers a computationally efficient and biologically plausible alternative to backpropagation (BP) by training neural networks through purely local, layer-wise optimization.
arXiv AI
Jun 3
What Benchmarks Don't Measure: The Case for Evaluating Abstention Competence in Autonomous Agents
arXiv:2606. 02965v1 Announce Type: new Abstract: Benchmarks for autonomous agents measure whether agents complete tasks, yet this framing is systematically blind to whether an agent should have proceeded at all.
arXiv AI
Jun 3
Large AI Models in Dental Healthcare: From General-Purpose Systems to Domain-Specific Foundation Models
arXiv:2606. 02914v1 Announce Type: new Abstract: Background: Oral diseases affect nearly 3.
Hugging Face Trending Papers
Jun 3
CleanCodec: Efficient and Robust Speech Tokenization via Perceptually Guided Encoding
Neural audio codecs are a key component of speech processing pipelines, compressing audio into discrete tokens for downstream modeling. However, existing codecs struggle to balance reconstruction quality with token efficiency, often encoding perceptually irrelevant information such as background noise and recording artifacts at the expense of linguistically and acoustically meaningful content.
Hugging Face Trending Papers
Jun 3
When Clients Stop Following: A Cognitive Conceptualization Diagram-driven Framework for Strategic Counseling
Large Language Models (LLMs) show promise in psychological counseling, yet existing benchmarks rely heavily on highly cooperative simulated clients. We observe a critical counselor-following phenomenon: these clients often rapidly shift from resistance to compliance after only a few turns, creating an illusion of therapeutic progress and inflating scores under current evaluation protocols through superficial empathy.
Hugging Face Trending Papers
Jun 3
From Symbolic to Geometric: Enabling Spatial Reasoning in Large Language Models
Recent large language models (LLMs) often appear to exhibit spatial reasoning ability; however, this capability is largely \emph{symbolic}, arising from pattern matching over spatial language rather than true \emph{geometric} reasoning over space. Because LLMs operate on discrete tokens, they lack native support for continuous spatial representations, explicit geometric computation, and structured spatial operators.
Hugging Face Trending Papers
Jun 3
DLLG: Dynamic Logit-Level Gating of LLM Experts
Leveraging multiple specialized LLMs can combine complementary strengths, but existing approaches trade adaptability for stability: routing commits prematurely, heuristic ensembling depends on fragile proxies, and parameter merging introduces interference. We propose DLLG (Dynamic Logit-Level Gating), a dynamic logit-level ensembling framework that learns token-level expert fusion from sparse response-level supervision.
Hugging Face Trending Papers
Jun 3
Measuring What Matters: Synthetic Benchmarks for Concept Bottleneck Models
Concept bottleneck models predict outcomes from high-level concepts detected in inputs. Although concepts provide a simple way to reap benefits from interpretability, very few datasets include concept labels.