CaliCausalRank: Calibrated Multi-Objective Ad Ranking with Robust Counterfactual Utility Optimization
arXiv:2602.18786v1 Announce Type: new Abstract: Ad ranking systems must simultaneously optimize multiple objectives including click-through rate (CTR), conversion rate (CVR), revenue, and user experience metrics. However, production systems face critical challenges: score scale inconsistency across traffic segments undermines threshold transferability,...
Boosting for Vector-Valued Prediction and Conditional Density Estimation
arXiv:2602.18866v1 Announce Type: new Abstract: Despite the widespread use of boosting in structured prediction, a general theoretical understanding of aggregation beyond scalar losses remains incomplete. We study vector-valued and conditional density prediction under general divergences and identify stability conditions under...
SCOTUStoday for Tuesday, February 24
On this day in 1803, the Supreme Court released its ruling in Marbury v. Madison, which established the principle of judicial review (or did it?). Mark the anniversary with us […]The postSCOTUStoday for Tuesday, February 24appeared first onSCOTUSblog.
Chill
Introduction No concept is more pervasive in the law of freedom of speech than chill.[1] The chilled speech doctrine guards against self-censorship: it permits First Amendment challenges based on the allegation that a law deters the plaintiff or others from...
Spanish ‘soonicorn’ Multiverse Computing releases free compressed AI model
Spanish startup Multiverse Computing has released a new version of its HyperNova 60B model on Hugging Face that, it says, bests Mistral's model.
Anthropic launches new push for enterprise agents with plug-ins for finance, engineering, and design
It's a major opportunity to grow Anthropic’s enterprise client base — and a significant threat to SaaS products currently performing those functions.
Neural Synchrony Between Socially Interacting Language Models
arXiv:2602.17815v1 Announce Type: new Abstract: Neuroscience has uncovered a fundamental mechanism of our social nature: human brain activity becomes synchronized with others in many social contexts involving interaction. Traditionally, social minds have been regarded as an exclusive property of living...
Information-Theoretic Storage Cost in Sentence Comprehension
arXiv:2602.18217v1 Announce Type: new Abstract: Real-time sentence comprehension imposes a significant load on working memory, as comprehenders must maintain contextual information to anticipate future input. While measures of such load have played an important role in psycholinguistic theories, they have...
SPQ: An Ensemble Technique for Large Language Model Compression
arXiv:2602.18420v1 Announce Type: new Abstract: This study presents an ensemble technique, SPQ (SVD-Pruning-Quantization), for large language model (LLM) compression that combines variance-retained singular value decomposition (SVD), activation-based pruning, and post-training linear quantization. Each component targets a different source of inefficiency:...
VIRAASAT: Traversing Novel Paths for Indian Cultural Reasoning
arXiv:2602.18429v1 Announce Type: new Abstract: Large Language Models (LLMs) have made significant progress in reasoning tasks across various domains such as mathematics and coding. However, their performance deteriorates in tasks requiring rich socio-cultural knowledge and diverse local contexts, particularly those...
On the Semantic and Syntactic Information Encoded in Proto-Tokens for One-Step Text Reconstruction
arXiv:2602.18301v1 Announce Type: cross Abstract: Autoregressive large language models (LLMs) generate text token-by-token, requiring n forward passes to produce a sequence of length n. Recent work, Exploring the Latent Capacity of LLMs for One-Step Text Reconstruction (Mezentsev and Oseledets), shows...
VeriSoftBench: Repository-Scale Formal Verification Benchmarks for Lean
arXiv:2602.18307v1 Announce Type: cross Abstract: Large language models have achieved striking results in interactive theorem proving, particularly in Lean. However, most benchmarks for LLM-based proof automation are drawn from mathematics in the Mathlib ecosystem, whereas proofs in software verification are...
BioBridge: Bridging Proteins and Language for Enhanced Biological Reasoning with LLMs
arXiv:2602.17680v1 Announce Type: new Abstract: Existing Protein Language Models (PLMs) often suffer from limited adaptability to multiple tasks and exhibit poor generalization across diverse biological contexts. In contrast, general-purpose Large Language Models (LLMs) lack the capability to interpret protein sequences...
AnCoder: Anchored Code Generation via Discrete Diffusion Models
arXiv:2602.17688v1 Announce Type: new Abstract: Diffusion language models offer a compelling alternative to autoregressive code generation, enabling global planning and iterative refinement of complex program logic. However, existing approaches fail to respect the rigid structure of programming languages and, as...
Grassmannian Mixture-of-Experts: Concentration-Controlled Routing on Subspace Manifolds
arXiv:2602.17798v1 Announce Type: new Abstract: Mixture-of-Experts models rely on learned routers to assign tokens to experts, yet standard softmax gating provides no principled mechanism to control the tradeoff between sparsity and utilization. We propose Grassmannian MoE (GrMoE), a routing framework...
Calibrated Adaptation: Bayesian Stiefel Manifold Priors for Reliable Parameter-Efficient Fine-Tuning
arXiv:2602.17809v1 Announce Type: new Abstract: Parameter-efficient fine-tuning methods such as LoRA enable practical adaptation of large language models but provide no principled uncertainty estimates, leading to poorly calibrated predictions and unreliable behavior under domain shift. We introduce Stiefel-Bayes Adapters (SBA),...
Causality by Abstraction: Symbolic Rule Learning in Multivariate Timeseries with Large Language Models
arXiv:2602.17829v1 Announce Type: new Abstract: Inferring causal relations in timeseries data with delayed effects is a fundamental challenge, especially when the underlying system exhibits complex dynamics that cannot be captured by simple functional mappings. Traditional approaches often fail to produce...
COMBA: Cross Batch Aggregation for Learning Large Graphs with Context Gating State Space Models
arXiv:2602.17893v1 Announce Type: new Abstract: State space models (SSMs) have recently emerged for modeling long-range dependency in sequence data, with much simplified computational costs than modern alternatives, such as transformers. Advancing SMMs to graph structured data, especially for large graphs,...
Understanding the Generalization of Bilevel Programming in Hyperparameter Optimization: A Tale of Bias-Variance Decomposition
arXiv:2602.17947v1 Announce Type: new Abstract: Gradient-based hyperparameter optimization (HPO) have emerged recently, leveraging bilevel programming techniques to optimize hyperparameter by estimating hypergradient w.r.t. validation loss. Nevertheless, previous theoretical works mainly focus on reducing the gap between the estimation and ground-truth...
When Remembering and Planning are Worth it: Navigating under Change
arXiv:2602.15274v1 Announce Type: new Abstract: We explore how different types and uses of memory can aid spatial navigation in changing uncertain environments. In the simple foraging task we study, every day, our agent has to find its way from its...
World-Model-Augmented Web Agents with Action Correction
arXiv:2602.15384v1 Announce Type: new Abstract: Web agents based on large language models have demonstrated promising capability in automating web tasks. However, current web agents struggle to reason out sensible actions due to the limitations of predicting environment changes, and might...
Common Belief Revisited
arXiv:2602.15403v1 Announce Type: new Abstract: Contrary to common belief, common belief is not KD4. If individual belief is KD45, common belief does indeed lose the 5 property and keep the D and 4 properties -- and it has none of...
Enhancing Building Semantics Preservation in AI Model Training with Large Language Model Encodings
arXiv:2602.15791v1 Announce Type: new Abstract: Accurate representation of building semantics, encompassing both generic object types and specific subtypes, is essential for effective AI model training in the architecture, engineering, construction, and operation (AECO) industry. Conventional encoding methods (e.g., one-hot) often...
S-PRESSO: Ultra Low Bitrate Sound Effect Compression With Diffusion Autoencoders And Offline Quantization
arXiv:2602.15082v1 Announce Type: cross Abstract: Neural audio compression models have recently achieved extreme compression rates, enabling efficient latent generative modeling. Conversely, latent generative models have been applied to compression, pushing the limits of continuous and discrete approaches. However, existing methods...
PolyNODE: Variable-dimension Neural ODEs on M-polyfolds
arXiv:2602.15128v1 Announce Type: cross Abstract: Neural ordinary differential equations (NODEs) are geometric deep learning models based on dynamical systems and flows generated by vector fields on manifolds. Despite numerous successful applications, particularly within the flow matching paradigm, all existing NODE...
Orchestration-Free Customer Service Automation: A Privacy-Preserving and Flowchart-Guided Framework
arXiv:2602.15377v1 Announce Type: new Abstract: Customer service automation has seen growing demand within digital transformation. Existing approaches either rely on modular system designs with extensive agent orchestration or employ over-simplified instruction schemas, providing limited guidance and poor generalizability. This paper...
TAROT: Test-driven and Capability-adaptive Curriculum Reinforcement Fine-tuning for Code Generation with Large Language Models
arXiv:2602.15449v1 Announce Type: new Abstract: Large Language Models (LLMs) are changing the coding paradigm, known as vibe coding, yet synthesizing algorithmically sophisticated and robust code still remains a critical challenge. Incentivizing the deep reasoning capabilities of LLMs is essential to...
ExpertWeaver: Unlocking the Inherent MoE in Dense LLMs with GLU Activation Patterns
arXiv:2602.15521v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) effectively scales model capacity while preserving computational efficiency through sparse expert activation. However, training high-quality MoEs from scratch is prohibitively expensive. A promising alternative is to convert pretrained dense models into sparse MoEs....
Beyond Static Pipelines: Learning Dynamic Workflows for Text-to-SQL
arXiv:2602.15564v1 Announce Type: new Abstract: Text-to-SQL has recently achieved impressive progress, yet remains difficult to apply effectively in real-world scenarios. This gap stems from the reliance on single static workflows, fundamentally limiting scalability to out-of-distribution and long-tail scenarios. Instead of...
LLM-to-Speech: A Synthetic Data Pipeline for Training Dialectal Text-to-Speech Models
arXiv:2602.15675v1 Announce Type: new Abstract: Despite the advances in neural text to speech (TTS), many Arabic dialectal varieties remain marginally addressed, with most resources concentrated on Modern Spoken Arabic (MSA) and Gulf dialects, leaving Egyptian Arabic -- the most widely...