Most video pretraining methods recover masked content within a clip rather than predicting the future, and autoregressive token prediction has lagged joint-embedding methods in representation quality. VANE proposes next-frame prediction in a frozen semantic embedding space, using a causal encoder and a lightweight generative decoder to preserve spatial detail, and extends the same objective to still images via local-to-global crops. This unifies image and video pretraining under a single scalable objective centered on temporal evolution, yielding strong gains on anticipation, recognition, and dense benchmarks.

ULME tackles the frictions between text embedding and text generation, which are usually handled by separate models with incompatible objectives. The paper proposes a post-training framework for causal decoder-only LLMs that inserts a chain of learnable slots between the query and answer, then couples the two tasks via a stop-gradient predictive loss so that generation actively shapes the embedding. Across eight scales of Qwen2.5 and Qwen3 (0.5B–8B), a single ULME checkpoint raises MTEB scores by 3.3–4.1 points over the strongest open baseline while remaining on par with generation-only fine-tuning on standard accuracy benchmarks.

The paper asks how to predict the performance of a safety probe before it is trained. Its core finding is that probe error follows two scaling laws: a power-law floor in model size and a Hill-curve approach to that floor as labels increase. This matters because it could let safety teams budget labels and choose architectures for new models without expensive grid search.

Singular-value spectra shape how transformer MLPs amplify different directions, yet their causal role in downstream capabilities is poorly understood. This paper introduces a post-hoc "Matthew" perturbation that reweights the singular values of MLP up_proj and down_proj matrices around their geometric mean—spiking inequality with $\alpha>0$ or smoothing it with $\alpha<0$—while preserving singular vectors and the geometric mean. Across five instruction-tuned Llama and Qwen models, the authors evaluate perturbed systems on 118 capability-labeled subtasks, auxiliary benchmarks, and personality probes, arguing that spectral inequality is a manipulable variable that can selectively trade off factual knowledge, language understanding, and deductive reasoning without retraining.

When a multilingual LLM flips its answer under user pressure, it is unclear whether it knew the correct answer and yielded (sycophancy) or simply lacked competence in that language. This paper introduces the SC-matrix, a $2 \times 2$ diagnostic crossing Competence ($C$) and Sycophancy ($S$) to decompose behavior into four cells: Robust, True Sycophancy, Honest Uncertainty, and Uninformed Deference. Their experiments across six languages and three models show that aggregate sycophancy rates hide very different failure mixtures, and that reasoning-based prompts outperform direct alignment instructions at reducing pressure-induced flips.

This paper investigates whether Group Relative Policy Optimisation (GRPO), previously applied to LLM-based speech recognition, can improve smaller encoder-decoder ASR models in a multilingual, low-resource setting. Using Whisper-large-v3 as a case study, the authors train SunflowerASR on 51 African languages and report state-of-the-art macro-averaged WER on AfriVox-v2 and SimbaBench. Key innovations include a headroom-based training example selection strategy and careful ablations isolating the reinforcement signal from mere additional training.

The paper attacks the combinatorial cost of maintaining separate LoRA adapters for every pretrained backbone–task pair. Its core idea, LoRA superposition, is to sum the low-rank updates learned independently on different backbones and apply the same composite update unchanged to every contributing model. The empirical finding is that frozen backbones implicitly select their own component from the sum, enabling a single shared adapter without explicit routing or cross-model alignment. If the phenomenon generalizes, it could enable modular adapter libraries that work across pretrained models without joint retraining.

Urban flooding threatens infrastructure but specialist hydrological modeling is often inaccessible to smaller municipalities. This paper proposes a GeoAI agentic framework that extracts terrain basins from public elevation data using discrete Morse theory, ranks them with a multi-criteria relative flood-priority score, and strictly limits the language model to recorded decision points—threshold selection, recommendation drafting, and self-review—under three human-in-the-loop checkpoints. The goal is transparent, screening-level flood-risk triage that keeps geospatial computation deterministic and recommendations traceable.

The paper tackles the problem of social world modeling, where an agent must anticipate how other parties might respond to its actions in multi-turn interactions. The key insight is that social environments are inherently stochastic—one action can trigger several plausible responses—so predicting only a single future or exploring alternatives through repeated simulation at inference time is either myopic or expensive. The authors propose DSWM, a 4B-parameter distributional model that outputs a compact set of response clusters, each with a probability and predicted immediate and final outcome values, trained from 50-rollout Monte Carlo targets via supervised fine-tuning and GRPO. The setup is evaluated across five environments with held-out scenario families and unseen interaction backbones.

Federated unsupervised domain adaptation (FUDA) aims to adapt a model to an unlabeled target domain using decentralized labeled sources without centralizing raw data. This paper proposes SKD-ETR, a one-shot FUDA framework that trains a randomly initialized student on the target domain via smoothed knowledge distillation from an ensemble of source teachers, while simultaneously refining those teachers back toward the student through exponential moving average (EMA) updates. The authors claim this bidirectional, communication-efficient loop yields competitive accuracy on standard benchmarks while remaining robust to noisy pseudo-labels.

This paper challenges the prevailing narrative that speculative-decoding acceptance rate inevitably decays as a chain-of-thought grows longer. The authors conduct the first systematic, full-length measurement using independent draft models—neither trained on target outputs—across all 500 MATH-500 problems, two decoding modes, and roughly 1.78 million verification rounds. After controlling for a greedy repetition pathology, they find that acceptance does not decay with position within the supported ranges (greedy 0–8K, sampling 0–12K) and actually rises slightly. They further show that failures concentrate on high-entropy reflection tokens rather than on late positions, and that a lightweight LoRA trajectory-alignment intervention fails to improve mean accepted length, redirecting draft-alignment objectives toward directly optimizing the acceptance criterion.

The paper introduces ChronoEvo, a benchmark of 1,709 real clinical-guideline revisions spanning 12 semantic change types, to test whether LLMs update recommendations when given evolving medical evidence. Its central finding is a persistent dissociation: models frequently recognize that a recommendation has changed yet fail to fully incorporate those changes, leaving a roughly 32-percentage-point recognition-to-incorporation gap even when revised evidence is explicitly provided. This establishes faithful knowledge incorporation as a distinct and under-measured dimension of clinical LLM reliability.

Understanding how reasoning models compute their chain-of-thought is challenging because sampled responses vary widely, making it hard to isolate the effect of a prompt intervention. This paper proposes behavioral counterfactuals: keep a generated response fixed and compare next-token distributions under a control prompt and an intervention prompt. The authors train a residual-stream edit module to minimize the $\mathrm{KL}$ divergence between the edited and counterfactual output distributions, then attribute recovery to individual token edits and validate with activation patching. On ethical reasoning tasks, they find that filler and question tokens mediate a substantial share of the intervention’s influence even when the model never verbally acknowledges the suggestion.

Time series anomaly detection has fragmented into siloed architectures—RNNs, Transformers, diffusion models, state space models, and LLMs—without a principled way to compare their detection assumptions. This survey attacks the chaos by separating detection paradigms (reconstruction, forecasting, generative, similarity-based, statistical, and LLM-driven) from backbone architectures, and formalizes a multivariate taxonomy that includes channel-correlation anomalies. It also delivers a critical empirical analysis of evaluation metrics and releases an open-source benchmark. The result is a much-needed map for researchers navigating a rapidly expanding landscape.

Current agentic systems often hallucinate or drift during multi-turn reasoning because they rely on unstructured token-level generation. This paper proposes SGUR, a training-free framework that grounds multi-step inference in structured hypothesis spaces using partial graph alignment and active information gain. Evaluated on a sequential medical-diagnosis benchmark derived from PrimeKG, the results suggest that tighter structural discipline can partially offset the need for ever-larger language models.

This mixed-methods study examines how university students perceive their generative AI skills changing over time and whether those perceived trajectories connect to shifts in learning practices and academic outcomes. Using a retrospective survey of 313 students and interviews with 18 across disciplines, the authors identify heterogeneous developmental patterns—most commonly rapid early improvement followed by a plateau—and find that self-reported academic gains are linked to assignment-process adaptation rather than to a specific trajectory. The work highlights uneven growth across skill domains and signals that institutions should tailor support beyond generic tool training, though the cross-sectional design cannot establish actual longitudinal change.

Multimodal in-context learning remains weak because MLLMs often hallucinate and fail to ground textual outputs in the visual evidence provided in demonstrations.
This work argues that the root bottleneck is poor visual grounding rather than a lack of ICL-specific training data.
The authors propose ProCoRe, which uses proposition-level contrastive reinforcement learning on non-ICL image–caption pairs to sharpen fine-grained visual discrimination.
The result is stronger multimodal ICL without catastrophic forgetting, plus a new personalized-captioning benchmark that forces models to rely on demonstrations instead of lexical priors.

The paper tackles the closed-world problem in cybersecurity intrusion detection, where supervised models trained on benign and insider-threat labels fail when confronted with entirely novel botnet activation attacks at test time. The core idea is a hybrid fuzzy ensemble that couples a gradient-optimized Takagi-Sugeno-Kang (TSK) classifier for known suspicious behaviors with a Fuzzy C-Means (FCM) module that flags out-of-distribution (OoD) samples via a raw Min Distance metric rather than traditional membership scores. The work is relevant because it directly targets the operational reality that security operations centers must detect attack vectors never seen during training, and it attempts to do so with an interpretable, rule-based architecture rather than a black-box neural network.

Personalized mobile GUI agents must decide both how user preferences alter execution and when they apply along a trajectory. Existing benchmarks only report aggregate task success, obscuring where and why personalization fails. This paper introduces PrefDiag-Bench, a diagnostic benchmark with 318 end-to-end tasks and 1,664 stage-wise probes that categorize preferences into five execution types and pinpoint bottlenecks in evidence selection and trigger recognition. The result is a reproducible tool set for moving beyond coarse success rates toward targeted improvement of personalization capabilities.

AI agents that act as statistical analysts evolve through model upgrades, prompt edits, and new tools, but each change risks inflating Type I error. This paper introduces continual validation: before any update is deployed, it is frozen and tested on newly simulated null data using exact binomial confidence bounds with a decaying per-update risk budget. The result is a lifetime guarantee that no invalid version passes, which matters because classical fixed-procedure guarantees break under adaptive, open-ended evolution.