Cross-Encoder Reranking

Large language models (LLMs) often produce confident yet incorrect responses, and uncertainty quantification is one potential solution to more robust usage. Recent works routinely rely on self-consistency to estimate aleatoric uncertainty (AU), yet this proxy collapses when models are overconfident and produce the same incorrect answer across samples. We analyze this regime and show that cross-model semantic disagreement is higher on incorrect answers precisely when AU is low. Motivated by this, we introduce an epistemic uncertainty (EU) term that operates in the black-box access setting: EU uses only generated text from a small, scale-matched ensemble and is computed as the gap between inter-model and intra-model sequence-semantic similarity. We then define total uncertainty (TU) as the sum of AU and EU. In a comprehensive study across five 7-9B instruction-tuned models and ten long-form tasks, TU improves ranking calibration and selective abstention relative to AU, and EU reliably flags confident failures where AU is low. We further characterize when EU is most useful via agreement and complementarity diagnostics.

Computing next-token likelihood ratios between two language models (LMs) is a standard task in training paradigms such as knowledge distillation. Since this requires both models to share the same probability space, it becomes challenging when the teacher and student LMs use different tokenizers, for instance, when edge-device deployment necessitates a smaller vocabulary size to lower memory overhead. This work addresses this vocabulary misalignment problem by uncovering an implicit recursive structure in the commonly deployed Byte-Pair Encoding (BPE) algorithm and utilizing it to create a probabilistic framework for \textit{cross-tokenizer likelihood scoring}. Our method enables sequence likelihood evaluation for vocabularies different from the teacher model native tokenizer, addressing two specific scenarios: when the student vocabulary is a subset of the teacher vocabulary, and the general case where it is arbitrary. In the subset regime, our framework computes exact likelihoods and provides next-token probabilities for sequential sampling with only $\mathcal{O}(1)$ model evaluations per token. When used for distillation, this yields up to a 12% reduction in memory footprint for the Qwen2.5-1.5B model while also improving baseline performance up to 4\% on the evaluated tasks. For the general case, we introduce a rigorous lossless procedure that leverages BPE recursive structure, complemented by a fast approximation that keeps large-vocabulary settings practical. Applied to GSM8K mathematical reasoning distillation, our method improves accuracy by over 2% the current state of the art. Code: https://github.com/truongbuu/cross-tokenizer-scoring

We present the TRIplet-based Distance-preserving Embedding Network for Trajectories (TRIDENT), a spatio-temporal representation framework for compressing and retrieving trajectories across scales, from badminton courts to large-scale urban environments. Existing methods often assume smooth, continuous motion, but real trajectories exhibit event-driven annotation, abrupt direction changes, GPS errors, irregular sampling, and domain shifts, exposing the inefficiency, limited generalization, and inability to robustly integrate temporal order with spatial sequence structure of prior models. TRIDENT addresses these challenges by combining GCN spatial embeddings with temporal features in a Dual-Attention Encoder (DAEncoder), along with a Nonlinear Tanh-Projection Attention Pooling (NTAP) module that preserves local order and robustness under noise. For metric learning, we introduce a Distance-preserving Multi-kernel Triplet Loss (DMT) to preserve pairwise spatio-temporal distances in the native feature space and their rank order within the embedding, thereby reducing geometry distortion and improving cross-domain generalization. Experiments on urban mobility and badminton datasets show that TRIDENT outperforms strong baselines in retrieval accuracy, efficiency, and cross-domain generalization. Furthermore, the learned embeddings capture spatio-temporal sequence patterns, facilitating tactical analysis of badminton rallies via silhouette-guided spectral clustering that provides more actionable insights than direct trajectory classification. An anonymous repo with code and data is in the supplement.

Class-Incremental Learning (CIL) traditionally assumes that all tasks share a similar domain distribution, limiting its applicability in real-world scenarios where data arrive from evolving environments. We introduce a new problem setting, Cross-Expanding Incremental Learning (XIL), which extends CIL by requiring models to handle class-incremental data across distinct domains and to expand class-domain associations bidirectionally. In this setting, new classes should be integrated into previously seen domains, while earlier classes are extended to newly encountered ones, a capability we refer to as bidirectional domain transferability (BiDoT). To address XIL, we present a new framework, Semantic Expansion through Evolving Domains (XEED), which leverages domain-specialized prompts, residual-guided representation modulation, and evolving prototype embeddings to expand class semantics across previously encountered domains. We further introduce the BiDoT Score, a novel metric for quantifying the degree of BiDoT. Extensive experiments on benchmark datasets with significant domain shifts demonstrate that XEED outperforms existing CIL baselines by a large margin in both standard accuracy and BiDoT scores, establishing a strong foundation for realistic continual learning under domain-evolving conditions.

The task of learning a diffusion-based neural sampler for drawing samples from an unnormalized target distribution can be viewed as a stochastic optimal control problem on path measures. However, the training of neural samplers can be challenging when the target distribution is multimodal with significant barriers separating the modes, potentially leading to mode collapse. We propose a framework named **Proximal Diffusion Neural Sampler (PDNS)** that addresses these challenges by tackling the stochastic optimal control problem via proximal point method on the space of path measures. PDNS decomposes the learning process into a series of simpler subproblems that create a path gradually approaching the desired distribution. This staged procedure traces a progressively refined path to the desired distribution and promotes thorough exploration across modes. For a practical and efficient realization, we instantiate each proximal step with a proximal weighted denoising cross-entropy (WDCE) objective. We demonstrate the effectiveness and robustness of PDNS through extensive experiments on both continuous and discrete sampling tasks, including challenging scenarios in molecular dynamics and statistical physics.

Multimodal retrieval still leans on embedding-based models like CLIP for fast vector search over pre-computed image embeddings. Yet, unlike text retrieval where joint-encoder rerankers are standard, comparable vision–language rerankers are largely absent. We find that seminal joint encoders such as BLIP are severely bottlenecked by an expensive visual feature-extraction stage, preventing practical deployment at scale. Motivated by this bottleneck, we introduce EDJE , an Efficient Discriminative Joint Encoder that precomputes vision tokens offline and compresses them via a lightweight attention-based adapter, so online inference runs only a compact joint encoder over a small set of visual tokens plus the text. EDJE preserves strong retrieval performance while drastically reducing storage and online compute, enabling high-throughput inference. Specifically, EDJE processes 50k image–text pairs/second while requiring 49kB of disk storage per image, matching prior art on Flickr (zero-shot) and COCO (fine-tuned) retrieval.

This paper analyzes Cross-Entropy (CE) loss in knowledge distillation (KD) for recommender systems. KD for recommender systems targets at distilling rankings, especially among items most likely to be preferred, and can only be computed on a small subset of items. Considering these features, we reveal the connection between CE loss and NDCG in the field of KD. We prove that when performing KD on an item subset, minimizing CE loss maximizes the lower bound of NDCG, only if an assumption of closure is satisfied. It requires that the item subset consists of the student's top items. However, this contradicts our goal of distilling rankings on the teacher's top items. We empirically demonstrate the vast gap between these two kinds of top items. To bridge the gap between our goal and theoretical support, we propose Rejuvenated Cross-Entropy for Knowledge Distillation (RCE-KD). It splits the top items given by the teacher into two subsets based on whether or not it is ranked high by the student. For the subset that defies the condition, a sampling strategy is devised to use teacher-student collaboration to approximate our assumption of closure. We also combine the losses on the two subsets adaptively. Extensive experiments demonstrate the effectiveness of our method. Our code is available at https://anonymous.4open.science/r/RCE-KD.

CD8+ “killer” T cells and CD4+ “helper” T cells play a central role in the adaptive immune system by recognizing antigens presented by Major Histocompatibility Complex (pMHC) molecules via T Cell Receptors (TCRs). Modeling binding between T cells and the pMHC complex is fundamental to understanding basic mechanisms of human immune response as well as in developing therapies. While transformer-based models such as TULIP have achieved impressive performance in this domain, their black-box nature precludes interpretability and thus limits a deeper mechanistic understanding of T cell response. Most existing post-hoc explainable AI (xAI) methods are confined to encoder-only, co-attention, or model-specific architectures and cannot handle encoder-decoder transformers used in TCR-pMHC modeling. To address this gap, we propose Quantifying Cross-Attention Interaction (QCAI), a new post-hoc method designed to interpret the cross-attention mechanisms in transformer decoders. Quantitative evaluation is a challenge for XAI methods; we have compiled TCR-XAI, a benchmark consisting of 274 experimentally determined TCR-pMHC structures to serve as ground truth for binding. Using these structures we compute physical distances between relevant amino acid residues in the TCR-pMHC interaction region and evaluate how well our method and others estimate the importance of residues in this region across the dataset. We show that QCAI achieves state-of-the-art performance on both interpretability and prediction accuracy under the TCR-XAI benchmark.

Sharpness-Aware Minimization (SAM) has proven effective in enhancing deep neural network training by simultaneously minimizing the training loss and the sharpness of the loss landscape, thereby guiding models toward flatter minima that are empirically linked to improved generalization. From another perspective, generalization can be seen as a model’s ability to remain stable under distributional variability. In particular, effective learning requires that updates derived from different subsets or resamplings of the same data distribution remain consistent. In this work, we investigate the connection between the flatness induced by SAM and the alignment of gradients across random subsets of the data distribution, and propose \textit{Align-SAM} as a novel strategy to further enhance model generalization. Align-SAM extends the core principles of SAM by promoting optimization toward flatter minima on a primary subset (the training set), while simultaneously enforcing low loss on an auxiliary subset drawn from the same distribution. This dual-objective approach leads to solutions that are not only resilient to local perturbations but also robust against distributional shifts in each training iteration. Empirical evaluations demonstrate that Align-SAM consistently improves generalization across diverse datasets and challenging settings, including scenarios with noisy labels and limited data availability.

CLIP (Contrastive Language-Image Pretraining) has become a popular choice for various downstream tasks. However, recent studies have questioned its ability to represent compositional concepts effectively. These works suggest that CLIP often acts like a bag-of-words (BoW) model, interpreting images and text as sets of individual concepts without grasping the structural relationships. In particular, CLIP struggles to correctly bind attributes to their corresponding objects when multiple objects are present in an image or text. In this work, we investigate why CLIP exhibits this BoW-like behavior. Our key finding is that CLIP does not lack binding information. Through linear probing, robustness tests with increasing object counts, and conjunctive search experiments, we show that attribute–object bindings are already encoded within CLIP’s text and image embeddings. The weakness lies in the cross-modal alignment, which fails to preserve this information. We show it can be accessed cross-modally with a simple linear transformation to text embeddings. This improves CLIP’s attribute-object binding performance and confirms that the information was already encoded unimodally. In practice, this means CLIP-based systems can be enhanced with a lightweight linear layer trained on existing embeddings, avoiding costly encoder retraining.

Graphon models have emerged as powerful tools for modeling complex network structures by capturing connection probabilities among nodes. A key challenge in their application lies in accurately characterizing the graphon function, particularly with respect to parameters that govern its smoothness, which significantly impact the estimation accuracy. In this article, we propose a novel graphon cross-validation method for selecting tuning parameters and estimation approaches. Our method is both theoretically sound and computationally efficient. We show that our proposed cross-validation score is asymptotically parallel to the estimation error. Through extensive simulations and real-world applications, we demonstrate that our method consistently delivers superior computational efficiency and accuracy.

Diffusion models have transformed image generation, yet controlling their outputs for diverse applications, including content moderation and creative customization, remains challenging. Existing approaches usually require task-specific training and struggle to generalise across both concrete (e.g., objects) and abstract (e.g.,4 styles) concepts. We propose CASteer (Cross-Attention Steering), a training-free framework for controllable image generation using steering vectors to influence a diffusion model’s hidden representations dynamically. CASteer precomputes concept-specific steering vectors by averaging neural activations from images generated for each target concept. During inference, it dynamically applies these vectors to modify outputs only when necessary, either removing undesired concepts from images where they appear or adding desired concepts to images where they are absent. This selective activation ensures precise, context-aware adjustments without altering unaffected regions. This approach enables precise control over a wide range of tasks, including removing harmful content, interpolating between desired attributes, replacing objects, all without model retraining. CASteer outperforms state-of-the-art techniques while preserving unrelated content and minimising unintended effects. Code is provided in the supplementary

Encoder-free architectures have been preliminarily explored in the 2D Large Multimodal Models (LMMs), yet it remains an open question whether they can be effectively applied to 3D understanding scenarios. In this paper, we present the first comprehensive investigation into the potential of encoder-free architectures to alleviate the challenges of encoder-based 3D LMMs. These long-standing challenges include the failure to adapt to varying point cloud resolutions during inference and the point features from the encoder not meeting the semantic needs of Large Language Models (LLMs). We identify key aspects for 3D LMMs to remove the pre-trained encoder and enable the LLM to assume the role of the 3D encoder: 1) We propose the LLM-embedded Semantic Encoding strategy in the pre-training stage, exploring the effects of various point cloud self-supervised losses. And we present the Hybrid Semantic Loss to extract high-level semantics. 2) We introduce the Hierarchical Geometry Aggregation strategy in the instruction tuning stage. This incorporates inductive bias into the LLM layers to focus on the local details of the point clouds. To the end, we present the first Encoder-free 3D LMM, **ENEL**. Our 7B model rivals the state-of-the-art model, PointLLM-PiSA-13B, achieving 57.91%, 61.0%, and 55.20% on the classification, captioning, and VQA tasks, respectively. Our results show that the encoder-free architecture is highly promising for replacing encoder-based architectures in the field of 3D understanding.