3 days left: Save up to $680 on your TechCrunch Disrupt 2026 ticket
Just 3 days left to save up to $680 on your TechCrunch Disrupt 2026 ticket. Offer ends on Friday, February 27 at 11:59 p.m. PT. Don't miss unparalleled, curated networking and valuable insights from 250+ tech leaders, and discover 300+...
TriTopic: Tri-Modal Graph-Based Topic Modeling with Iterative Refinement and Archetypes
arXiv:2602.19079v1 Announce Type: new Abstract: Topic modeling extracts latent themes from large text collections, but leading approaches like BERTopic face critical limitations: stochastic instability, loss of lexical precision ("Embedding Blur"), and reliance on a single data perspective. We present TriTopic,...
Astra: Activation-Space Tail-Eigenvector Low-Rank Adaptation of Large Language Models
arXiv:2602.19111v1 Announce Type: new Abstract: Parameter-Efficient Fine-Tuning (PEFT) methods, especially LoRA, are widely used for adapting pre-trained models to downstream tasks due to their computational and storage efficiency. However, in the context of LoRA and its variants, the potential of...
Facet-Level Persona Control by Trait-Activated Routing with Contrastive SAE for Role-Playing LLMs
arXiv:2602.19157v1 Announce Type: new Abstract: Personality control in Role-Playing Agents (RPAs) is commonly achieved via training-free methods that inject persona descriptions and memory through prompts or retrieval-augmented generation, or via supervised fine-tuning (SFT) on persona-specific corpora. While SFT can be...
Anatomy of Agentic Memory: Taxonomy and Empirical Analysis of Evaluation and System Limitations
arXiv:2602.19320v1 Announce Type: new Abstract: Agentic memory systems enable large language model (LLM) agents to maintain state across long interactions, supporting long-horizon reasoning and personalization beyond fixed context windows. Despite rapid architectural development, the empirical foundations of these systems remain...
The Geometry of Multi-Task Grokking: Transverse Instability, Superposition, and Weight Decay Phase Structure
arXiv:2602.18523v1 Announce Type: new Abstract: Grokking -- the abrupt transition from memorization to generalization long after near-zero training loss -- has been studied mainly in single-task settings. We extend geometric analysis to multi-task modular arithmetic, training shared-trunk Transformers on dual-task...
GIST: Targeted Data Selection for Instruction Tuning via Coupled Optimization Geometry
arXiv:2602.18584v1 Announce Type: new Abstract: Targeted data selection has emerged as a crucial paradigm for efficient instruction tuning, aiming to identify a small yet influential subset of training examples for a specific target task. In practice, influence is often measured...
In-Context Planning with Latent Temporal Abstractions
arXiv:2602.18694v1 Announce Type: new Abstract: Planning-based reinforcement learning for continuous control is bottlenecked by two practical issues: planning at primitive time scales leads to prohibitive branching and long horizons, while real environments are frequently partially observable and exhibit regime shifts...
Rank-Aware Spectral Bounds on Attention Logits for Stable Low-Precision Training
arXiv:2602.18851v1 Announce Type: new Abstract: Attention scores in transformers are bilinear forms $S_{ij} = x_i^\top M x_j / \sqrt{d_h}$ whose maximum magnitude governs overflow risk in low-precision training. We derive a \emph{rank-aware concentration inequality}: when the interaction matrix $M =...
Deep Learning for Dermatology: An Innovative Framework for Approaching Precise Skin Cancer Detection
arXiv:2602.17797v1 Announce Type: cross Abstract: Skin cancer can be life-threatening if not diagnosed early, a prevalent yet preventable disease. Globally, skin cancer is perceived among the finest prevailing cancers and millions of people are diagnosed each year. For the allotment...
Condition-Gated Reasoning for Context-Dependent Biomedical Question Answering
arXiv:2602.17911v1 Announce Type: cross Abstract: Current biomedical question answering (QA) systems often assume that medical knowledge applies uniformly, yet real-world clinical reasoning is inherently conditional: nearly every decision depends on patient-specific factors such as comorbidities and contraindications. Existing benchmarks do...
Thinking by Subtraction: Confidence-Driven Contrastive Decoding for LLM Reasoning
arXiv:2602.18232v1 Announce Type: new Abstract: Recent work on test-time scaling for large language model (LLM) reasoning typically assumes that allocating more inference-time computation uniformly improves correctness. However, prior studies show that reasoning uncertainty is highly localized: a small subset of...
LATMiX: Learnable Affine Transformations for Microscaling Quantization of LLMs
arXiv:2602.17681v1 Announce Type: cross Abstract: Post-training quantization (PTQ) is a widely used approach for reducing the memory and compute costs of large language models (LLMs). Recent studies have shown that applying invertible transformations to activations can significantly improve quantization robustness...
ADAPT: Hybrid Prompt Optimization for LLM Feature Visualization
arXiv:2602.17867v1 Announce Type: cross Abstract: Understanding what features are encoded by learned directions in LLM activation space requires identifying inputs that strongly activate them. Feature visualization, which optimizes inputs to maximally activate a target direction, offers an alternative to costly...
Joint Parameter and State-Space Bayesian Optimization: Using Process Expertise to Accelerate Manufacturing Optimization
arXiv:2602.17679v1 Announce Type: new Abstract: Bayesian optimization (BO) is a powerful method for optimizing black-box manufacturing processes, but its performance is often limited when dealing with high-dimensional multi-stage systems, where we can observe intermediate outputs. Standard BO models the process...
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...
Asking Forever: Universal Activations Behind Turn Amplification in Conversational LLMs
arXiv:2602.17778v1 Announce Type: new Abstract: Multi-turn interaction length is a dominant factor in the operational costs of conversational LLMs. In this work, we present a new failure mode in conversational LLMs: turn amplification, in which a model consistently prolongs multi-turn...
Memory-Based Advantage Shaping for LLM-Guided Reinforcement Learning
arXiv:2602.17931v1 Announce Type: new Abstract: In environments with sparse or delayed rewards, reinforcement learning (RL) incurs high sample complexity due to the large number of interactions needed for learning. This limitation has motivated the use of large language models (LLMs)...
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...
Connecting the dots in trustworthy Artificial Intelligence: From AI principles, ethics, and key requirements to responsible AI systems and regulation
Trustworthy Artificial Intelligence (AI) is based on seven technical requirements sustained over three main pillars that should be met throughout the system’s entire life cycle: it should be (1) lawful, (2) ethical, and (3) robust, both from a technical and...
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...
PERSONA: Dynamic and Compositional Inference-Time Personality Control via Activation Vector Algebra
arXiv:2602.15669v1 Announce Type: new Abstract: Current methods for personality control in Large Language Models rely on static prompting or expensive fine-tuning, failing to capture the dynamic and compositional nature of human traits. We introduce PERSONA, a training-free framework that achieves...
GlobeDiff: State Diffusion Process for Partial Observability in Multi-Agent Systems
arXiv:2602.15776v1 Announce Type: new Abstract: In the realm of multi-agent systems, the challenge of \emph{partial observability} is a critical barrier to effective coordination and decision-making. Existing approaches, such as belief state estimation and inter-agent communication, often fall short. Belief-based methods...
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...
EduResearchBench: A Hierarchical Atomic Task Decomposition Benchmark for Full-Lifecycle Educational Research
arXiv:2602.15034v1 Announce Type: cross Abstract: While Large Language Models (LLMs) are reshaping the paradigm of AI for Social Science (AI4SS), rigorously evaluating their capabilities in scholarly writing remains a major challenge. Existing benchmarks largely emphasize single-shot, monolithic generation and thus...
CircuChain: Disentangling Competence and Compliance in LLM Circuit Analysis
arXiv:2602.15037v1 Announce Type: cross Abstract: As large language models (LLMs) advance toward expert-level performance in engineering domains, reliable reasoning under user-specified constraints becomes critical. In circuit analysis, for example, a numerically correct solution is insufficient if it violates established methodological...
Indic-TunedLens: Interpreting Multilingual Models in Indian Languages
arXiv:2602.15038v1 Announce Type: cross Abstract: Multilingual large language models (LLMs) are increasingly deployed in linguistically diverse regions like India, yet most interpretability tools remain tailored to English. Prior work reveals that LLMs often operate in English centric representation spaces, making...
GRACE: an Agentic AI for Particle Physics Experiment Design and Simulation
arXiv:2602.15039v1 Announce Type: cross Abstract: We present GRACE, a simulation-native agent for autonomous experimental design in high-energy and nuclear physics. Given multimodal input in the form of a natural-language prompt or a published experimental paper, the agent extracts a structured...