Thyroid ultrasound reporting requires joint assessment of nodule boundaries and TI-RADS risk categories, yet annotator variability creates inconsistent supervision that destabilizes standard multitask learning. This paper proposes RLAR (Representation-Level Adversarial Regularization), which uses normalized adversarial directions in latent space as geometric probes of task sensitivity and penalizes excessive angular alignment between task gradients to control negative transfer. Combined with a clinically guided embedding that distills TI-RADS-aligned radiomics targets during training, the framework aims to stabilize joint segmentation and classification while grounding predictions in interpretable evidence.

This paper reframes plasticity loss in deep reinforcement learning as an optimization pathology rather than capacity degradation. The core claim—dubbed the Optimization-Centric Plasticity (OCP) hypothesis—is that parameters become trapped in local optima from previous tasks, which then become poor optima for new tasks. The authors prove that neuron dormancy is mathematically equivalent to zero-gradient states and show that plasticity recovers when tasks differ sufficiently, suggesting networks retain capacity but lose it to task-specific optimization landscapes.

Designing high-performance system heuristics traditionally requires human experts to navigate multi-step conceptual shifts. This paper introduces Engram, an agentic architecture that sidesteps the 'coherence ceiling' of single-context LLM agents and the 'evolutionary neighborhood bias' of code-mutation systems by decoupling long-horizon exploration into sequential agent handoffs. Each agent distills findings into a persistent Research Digest, enabling cumulative progress without context degradation.

Standard AlphaZero-style tree search for LLM reasoning suffers from a scaling failure: on GSM8K and Game24, accuracy actually drops as the search budget increases beyond moderate levels. This paper introduces ReSCALE, which replaces PUCT selection and Dirichlet noise with Gumbel sampling and Sequential Halving—a best-arm identification technique from multi-armed bandits. The key insight is that root action-selection design is critical for budget-scalable reasoning without any changes to the model or its training.

ViCLSR adapts supervised contrastive learning (SimCSE-style) to Vietnamese NLU by converting NLI entailment and contradiction pairs into positive and negative training signals. Built on XLM-R Large (550M), the framework improves sentence embeddings for low-resource Vietnamese, reporting gains of +6.97% F1 over PhoBERT on ViNLI and state-of-the-art results across five downstream tasks including fact-checking and machine reading comprehension.

This paper investigates whether neural text-to-speech systems capture consonant-induced F0 perturbation—fine-grained phonetic effects where voiceless obstruents raise and voiced obstruents lower fundamental frequency relative to sonorants. The authors propose a segmental-level prosodic probing framework comparing Tacotron 2 and FastSpeech 2 against natural speech, stratifying by lexical frequency to test memorization versus abstraction. This matters because TTS evaluation often misses sub-phonemic articulatory detail that distinguishes human-like phonetic competence from surface pattern matching.

BadGraph proposes the first universal adversarial attack on text-attributed graphs (TAGs) that works across both GNN and LLM backbones. The core idea: use an LLM agent to perturb topology and text jointly, creating 'cross-modal shortcuts' to mislead models without gradient access. This matters because TAG security is understudied and existing attacks fail when models use rich text encoders like SBERT or TAPE.

Forward-looking sonar images suffer from severe speckle noise, acoustic shadows, and energy attenuation that break standard semi-supervised teacher-student frameworks. This paper proposes CTFS, a collaborative multi-teacher architecture where one general teacher and two sonar-specific teachers (simulating acoustic shadows and energy decay) alternate to guide a student model. A cross-teacher reliability assessment mechanism filters noisy pseudo-labels by measuring prediction consistency across teacher views. The work matters because sonar annotation is expensive and existing methods fail with <10% labels due to domain mismatch.

Abductive reasoning—inferring the most probable hypothesis from incomplete observations—remains a critical gap for LLMs despite advances in deductive and inductive tasks. This paper introduces Graph of States (GoS), a neuro-symbolic framework that structures multi-agent collaboration through a causal graph (encoding belief states) and a state machine (governing navigation). By grounding reasoning in explicit symbolic constraints rather than unstructured context, GoS aims to eliminate Evidence Fabrication, Context Drift, Failed Backtracking, and Early Stopping that plague Chain-of-Thought and Tree-of-Thought when adapted to dynamic, non-monotonic abductive tasks like medical diagnosis and distributed systems failure analysis.

ConsRoute tackles the challenge of routing queries across cloud-edge-device LLM tiers by proposing a consistency-aware approach that uses reranker-based semantic similarity rather than scalar quality gaps. The core innovation lies in reusing device-side LLM (DLM) prefilling hidden states as query representations and applying cluster-specific adaptive thresholds learned via Bayesian optimization. This addresses the tension between response quality and latency/cost in resource-constrained mobile environments, claiming to achieve ≥95% of cloud accuracy while cutting latency and cost by ~40%.

This paper evaluates three inference-time strategies—self-consistency with temperature/top-p sampling, dual-model cross-verification, and iterative self-reflection—to improve multi-step reasoning in LLMs without parameter updates. The core premise is that aggregating diverse reasoning traces or validating across models yields more reliable outputs than single-pass decoding. The work addresses a practical need for deployment scenarios where retraining is infeasible, though the experimental scope is limited by unclear model specifications and dataset choices.

Domain Elastic Transform (DET) addresses the registration of high-dimensional vector-valued functions on irregular, sparse manifolds—a critical bottleneck in spatial transcriptomics where gene expression data resides on scattered cell positions rather than regular grids. The core idea is a Bayesian framework that treats registration as elastic domain deformation guided by a joint spatial-functional likelihood, bypassing the lossy voxelization required by image-based methods while exploiting functional signals that pure geometric point-set registration ignores. This matters because it enables training-free analysis of massive atlases (e.g., MERFISH, Stereo-seq) without sacrificing single-cell resolution.

This paper tackles multimodal hate speech detection where hateful intent emerges from complex interactions between text and images—what the authors call "more than the sum of its parts." The core innovation is the Stratified Multimodal Interaction (SMI) paradigm, which categorizes eight distinct cross-modal interaction patterns into three difficulty levels (Easy, Normal, Hard), coupled with the ARCADE framework that simulates an asymmetric courtroom debate between Prosecutor, Defender, and Judge agents to decipher subtle intent shifts. This matters because current detection systems fail when hateful content is constructed implicitly through benign-seeming modalities that only become toxic in combination.

QMoP tackles the computational bottleneck in multimodal LLMs caused by excessive visual tokens, which dwarf text tokens in memory and compute costs. The paper proposes a Query Guided Mixture-of-Projector that dynamically combines three compression strategies—pooling for global semantics, resampling for high-level features, and pruning for fine-grained details—via a learned router. This adaptive approach matters because fixed compression rules inherently sacrifice different information types (global context vs. local details) depending on the task.

DeepXplain tackles the opacity of autonomous APT defense by integrating explainability signals directly into reinforcement learning rather than treating explanation as a post-hoc add-on. The framework augments provenance-graph-based DRL with an alignment loss that ties policy decisions to GNN-derived structural explanations and temporal attributions, coupled with a confidence-aware reward shaping term. The core claim is that this tight coupling improves both task performance (F1-score from 0.887 to 0.915) and explanation quality (confidence 0.86, fidelity 0.79) compared to black-box alternatives.

Host-acting agents let users state goals while the system figures out how to achieve them. This paper argues this convenience creates a novel attack surface: semantic under-specification. When users specify outcomes but not safety boundaries, agents must fill in missing semantics—and may choose security-divergent plans even when no attacker is present and the goal is benign.

Current multimodal large language models rely on expensive annotated data or teacher distillation for reasoning improvements. This paper proposes an unsupervised self-evolution framework that trains without ground-truth labels or external reward models by instantiating dual roles—an Actor that generates multiple reasoning trajectories and a frozen Judge that modulates consistency-based rewards. The method employs group-wise distributional modeling using Group Relative Policy Optimization (GRPO) to convert absolute scores into relative advantages, achieving up to +5.9 absolute accuracy gains on MathVision while maintaining healthier training entropy than majority-voting baselines.

This paper investigates whether AI-assisted writing improves essay quality at the cost of homogenizing student thinking. Analyzing 6,875 essays across five conditions (Human-only, AI-only, and three Human+AI prompt strategies), the authors identify a Quality-Homogenization Tradeoff whereby substantial quality gains co-occur with structural convergence. The effect is dimension-specific: cohesion architecture loses 70–78% of its variance while perspective plurality diversifies, and prompt specificity can reverse homogenization into diversification on argument depth.

Sonny tackles the compute barrier in medium-range weather forecasting by proposing a hierarchical transformer that trains on a single A40 GPU in 5.5 days. The core idea is a two-stage StepsNet pipeline: a narrow 'slow path' processes large-scale dynamics (U,V,Z,P) first, then a full-width 'fast path' integrates thermodynamics (T,Q). Combined with EMA during training, randomized dynamics forecasting, and pressure-weighted losses, Sonny aims to deliver competitive forecast skill without the TPU/GPU cluster requirements of models like Pangu-Weather or GraphCast.

Existing counterfactual image generation methods produce either global changes or require tedious user-defined masks. This paper proposes Positional Seg-CFT, which subdivides anatomical structures into regional segments (e.g., proximal, mid, distal) and derives independent measurements per region from pretrained segmentors. The extension enables spatially localized interventions for modeling regional disease progression, demonstrated on coronary CT angiography.