长上下文

Identifying the functional identity of individual neurons is essential for interpreting circuit dynamics, yet it remains a major challenge in large-scale _in vivo_ recordings where anatomical and molecular labels are often unavailable. Here we introduce NuCLR, a self-supervised framework that learns context-aware representations of neuron identity by modeling each neuron's role within the broader population. NuCLR employs a spatio-temporal transformer that captures both within-neuron dynamics and across-neuron interactions. It is trained with a sample-wise contrastive objective that encourages temporally-stable and discriminative embeddings. Across multiple open-access datasets, NuCLR outperforms prior methods in both cell type and brain region classification. Critically, it exhibits strong zero-shot generalization to entirely new populations, without any retraining or access to stimulus labels. Furthermore, we demonstrate that our framework scales effectively with data size. Overall, our results demonstrate that modeling population context is crucial for understanding neuron identity and that rich signal for cell-typing and neuron localization is present in neural activity alone. Code available at: https://github.com/nerdslab/nuclr.

In-context Ranking (ICR) is an emerging paradigm for Information Retrieval (IR), which leverages contextual understanding of LLMs by directly incorporating the task description, candidate documents, and the query into the model's input prompt and tasking the LLM to identify relevant document(s). While it is effective, efficiency is a significant challenge in this paradigm, especially as the candidate list grows due to quadratic/super-linear scaling of attention operation with context length. To this end, this paper first identifies inherent and exploitable structures in the attention of LLMs finetuned for ICR: (1) inter-document block sparsity: attention is dense within each document block but sparse across different documents in the context; and (2) query-document block relevance: the attention scores from certain query tokens to a document block in middle layers strongly correlate with that document's actual relevance. Motivated by these observations, we introduce BlockRank (Blockwise In-context Ranking), a novel method that adapts the attention operation in an LLM by (a) architecturally enforcing the observed inter-document block sparsity, reducing attention complexity from quadratic to linear without loss in performance, and (b) optimizing query-document block relevance for true relevant documents during fine-tuning using an auxiliary contrastive training objective, improving retrieval in attention. Experiments on BEIR, MSMarco and NQ with Mistral-7B demonstrate that BlockRank Mistral matches or outperforms existing SOTA listwise rankers and controlled fine-tuned baseline while being significantly more efficient at inference (4.7x for 100 MSMarco documents in context) and scaling gracefully to long-context shortlists, around 500 documents in-context (approximately 100K context length) within a second, presenting a scalable and effective solution for ICR.

Processing structured tabular data, particularly large and lengthy tables, constitutes a fundamental yet challenging task for large language models (LLMs). However, existing long-context benchmarks like Needle-in-a-Haystack primarily focus on unstructured text, neglecting the challenge of diverse structured tables. Meanwhile, previous tabular benchmarks mainly consider downstream tasks that require high-level reasoning abilities, and overlook models' underlying fine-grained perception of individual table cells, which is crucial for practical and robust LLM-based table applications. To address this gap, we introduce \textsc{NeedleInATable} (NIAT), a new long-context tabular benchmark that treats each table cell as a ``needle'' and requires models to extract the target cell based on cell locations or lookup questions. Our comprehensive evaluation of various LLMs and multimodal LLMs reveals a substantial performance gap between popular downstream tabular tasks and the simpler NIAT task, suggesting that they may rely on dataset-specific correlations or shortcuts to obtain better benchmark results but lack truly robust long-context understanding towards structured tables. Furthermore, we demonstrate that using synthesized NIAT training data can effectively improve performance on both NIAT task and downstream tabular tasks, which validates the importance of NIAT capability for LLMs' genuine table understanding ability. Our data, code and models will be released to facilitate future research.

Although applications involving long-context inputs are crucial for the effective utilization of large language models (LLMs), they also result in increased computational costs and reduced performance. To address this challenge, we propose an efficient, training-free prompt compression method that retains key information within compressed prompts. We identify specific attention heads in transformer-based LLMs, which we designate as evaluator heads, that are capable of selecting tokens in long inputs that are most significant for inference. Building on this discovery, we develop EHPC, an Evaluator Head-based Prompt Compression method, which enables LLMs to rapidly "skim through'' input prompts by leveraging only the first few layers with evaluator heads during the pre-filling stage, subsequently passing only the important tokens to the model for inference. EHPC achieves state-of-the-art results across two mainstream benchmarks: prompt compression and long-context inference acceleration. Consequently, it effectively improves performance with the reduced costs associated with commercial API calls compared to prompt compressing methods. We further demonstrate that EHPC attains competitive results compared to key-value cache-based acceleration methods, thereby highlighting its potential to enhance the efficiency of LLMs for long-context tasks.

Transformers have revolutionized nucleotide sequence analysis, yet capturing long‑range dependencies remains challenging. Recent studies show that autoregressive transformers often exhibit Markovian behavior by relying on fixed-length context windows for next-token prediction. However, standard self-attention mechanisms are computationally inefficient for long sequences due to their quadratic complexity and do not explicitly enforce global transition consistency. We introduce CARMANIA (Context-Aware Regularization with Markovian Integration for Attention-Based Nucleotide Analysis), a self-supervised pretraining framework that augments next-token (NT) prediction with a transition-matrix (TM) loss. The TM loss aligns predicted token transitions with empirically derived n-gram statistics from each input sequence, encouraging the model to capture higher-order dependencies beyond local context. This integration enables CARMANIA to learn organism-specific sequence structures that reflect both evolutionary constraints and functional organization. We evaluate CARMANIA across diverse genomic tasks, including regulatory element prediction, functional gene classification, taxonomic inference, antimicrobial resistance detection, and biosynthetic gene cluster classification. CARMANIA outperforms the previous best long-context model by at least 7\%, matches state-of-the-art on shorter sequences (exceeding prior results on 20/40 tasks while running $\sim$2.5$\times$ faster), and shows particularly strong improvements on enhancer and housekeeping gene classification tasks—including up to a 34\% absolute gain in Matthews correlation coefficient (MCC) for enhancer prediction. The TM loss boosts accuracy in 33 of 40 tasks, especially where local motifs or regulatory patterns drive prediction. This enables more effective modeling of sequence-dependent biological features while maintaining robustness across non-coding and low-signal regions. Code available at https://github.com/EESI/carmania.

Modeling human decision-making is central to applications such as recommendation, preference learning, and human-AI alignment. While many classic models assume context-independent choice behavior, a large body of behavioral research shows that preferences are often influenced by the composition of the choice set itself---a phenomenon known as the context effect or Halo effect. These effects can manifest as pairwise (first-order) or even higher-order interactions among the available alternatives. Recent models that attempt to capture such effects either focus on the featureless setting or, in the feature-based setting, rely on restrictive interaction structures or entangle interactions across all orders, which limits interpretability. In this work, we propose DeepHalo, a neural modeling framework that incorporates features while enabling explicit control over interaction order and principled interpretation of context effects. Our model enables systematic identification of interaction effects by order and serves as a universal approximator of context-dependent choice functions when specialized to a featureless setting. Experiments on synthetic and real-world datasets demonstrate strong predictive performance while providing greater transparency into the drivers of choice.

Recent language models exhibit strong reasoning capabilities, yet the influence of long-context capacity on reasoning remains underexplored. In this work, we hypothesize that current limitations in reasoning stem, in part, from insufficient long-context capacity, motivated by empirical observations such as i) higher context window length often leads to stronger reasoning performance, and ii) failed reasoning cases resemble failed long-context cases. To test this hypothesis, we examine whether enhancing a model’s long-context ability before Supervised Fine-Tuning (SFT) leads to improved reasoning performance. Specifically, we compared models with identical architectures and fine-tuning data but varying levels of long-context capacity. Our results reveal a consistent trend: models with stronger long-context capacity achieve significantly higher accuracy on reasoning benchmarks after SFT. Notably, these gains persist even on tasks with short input lengths, indicating that long-context training offers generalizable benefits for reasoning performance. These findings suggest that long-context modeling is not just essential for processing lengthy inputs, but also serves as a critical foundation for reasoning. We advocate for treating long-context capacity as a first-class objective in the design of future language models.

Large language models (LLMs) have demonstrated significant improvements in contextual understanding. However, their ability to attend to truly critical information during long-context reasoning and generation still falls behind the pace. Specifically, our preliminary experiments reveal that certain distracting patterns can misdirect the model’s attention during inference, and removing these patterns substantially improves reasoning accuracy and generation quality. We attribute this phenomenon to spurious correlations in the training data, which obstruct the model’s capacity to infer authentic causal instruction–response relationships. This phenomenon may induce redundant reasoning processes, potentially resulting in significant inference overhead and, more critically, the generation of erroneous or suboptimal responses. To mitigate this, we introduce a two-stage framework called Learning to Focus (LeaF) leveraging intervention-based inference to disentangle confounding factors. In the first stage, LeaF employs gradient-based comparisons with an advanced teacher to automatically identify confounding tokens based on causal relationships in the training corpus. Then, in the second stage, it prunes these tokens during distillation to enact intervention, aligning the student’s attention with the teacher’s focus distribution on truly critical context tokens. Experimental results demonstrate that LeaF not only achieves an absolute improvement in various mathematical reasoning, code generation and multi-hop question answering benchmarks but also effectively suppresses attention to confounding tokens during inference, yielding a more interpretable and reliable reasoning model.

In-context learning, the ability of large language models to perform tasks using only examples provided in the prompt, has recently been adapted for time series forecasting. This paradigm enables zero-shot prediction, where past values serve as context for forecasting future values, making powerful forecasting tools accessible to non-experts and increasing the performance when training data are scarce. Most existing zero-shot forecasting approaches rely on transformer architectures, which, despite their success in language, often fall short of expectations in time series forecasting, where recurrent models like LSTMs frequently have the edge. Conversely, while LSTMs are well-suited for time series modeling due to their state-tracking capabilities, they lack strong in-context learning abilities. We introduce *TiRex* that closes this gap by leveraging xLSTM, an enhanced LSTM with competitive in-context learning skills. Unlike transformers, state-space models, or parallelizable RNNs such as RWKV, TiRex retains state tracking, a critical property for long-horizon forecasting. To further facilitate its state-tracking ability, we propose a training-time masking strategy called CPM. TiRex sets a new state of the art in zero-shot time series forecasting on the Hugging Face benchmarks *GiftEval* and *Chronos-ZS*, outperforming significantly larger models including *TabPFN-TS* (Prior Labs), *Chronos Bolt* (Amazon), *TimesFM* (Google), and *Moirai* (Salesforce) across both short- and long-term forecasts.

We demonstrate that geometrically distinctive keys during LLM inference tend to have high attention scores. Based on the phenomenon we propose KeyDiff, a training-free KV cache eviction method based solely on key similarity. Unlike other KV cache eviction methods, KeyDiff can process arbitrarily long prompts within strict resource constraints and efficiently generate responses. We provide a theoretical basis for KeyDiff by relating key diversity with attention scores. These results imply KeyDiff can efficiently identify the most important tokens to retain. Notably KeyDiff does not rely on attention scores, allowing the use of optimized attention mechanisms like FlashAttention. Under a strict memory allowance, we demonstrate the effectiveness of KeyDiff for the Llama and Qwen model families by observing a performance gap of less than 0.04\% with 8K cache budget (~23\% KV cache reduction) from the non-evicting baseline on LongBench for Llama 3.1-8B and Llama 3.2-3B. We also observe near baseline performance for Deepseek-R1-Distill-Llama-8B on the Math500 reasoning benchmark and decrease end-to-end inference latency by up to 30\% compared to the other token-eviction methods.

High-quality long-context instruction data is essential for aligning long-context large language models (LLMs). Despite the public release of models like Qwen and Llama, their long-context instruction data remains proprietary. Human annotation is costly and challenging, while template-based synthesis methods limit scale, diversity, and quality. We introduce LongMagpie, a self-synthesis framework that automatically generates large-scale long-context instruction data. Our key insight is that aligned long-context LLMs, when presented with a document followed by special tokens preceding a user turn, auto-regressively generate contextually relevant queries. By harvesting these document-query pairs and the model's responses, LongMagpie produces high-quality instructions without human effort. Experiments on HELMET, RULER, and Longbench v2 demonstrate that LongMagpie achieves leading performance on long-context tasks while maintaining competitive performance on short-context tasks, establishing it as a simple and effective approach for open, diverse, and scalable long-context instruction data synthesis.

Spiking Neural Networks (SNNs) demonstrate significant potential for energy-efficient neuromorphic computing through an event-driven paradigm. While training methods and computational models have greatly advanced, SNNs struggle to achieve competitive performance in visual long-sequence modeling tasks. In artificial neural networks, the effective receptive field (ERF) serves as a valuable tool for analyzing feature extraction capabilities in visual long-sequence modeling. Inspired by this, we introduce the Spatio-Temporal Effective Receptive Field (ST-ERF) to analyze the ERF distributions across various Transformer-based SNNs. Based on the proposed ST-ERF, we reveal that these models suffer from establishing a robust global ST-ERF, thereby limiting their visual feature modeling capabilities. To overcome this issue, we propose two novel channel-mixer architectures: \underline{m}ulti-\underline{l}ayer-\underline{p}erceptron-based m\underline{ixer} (MLPixer) and \underline{s}plash-and-\underline{r}econstruct \underline{b}lock (SRB). These architectures enhance global spatial ERF through all timesteps in early network stages of Transformer-based SNNs, improving performance on challenging visual long-sequence modeling tasks. Extensive experiments conducted on the Meta-SDT variants and across object detection and semantic segmentation tasks further validate the effectiveness of our proposed method. Beyond these specific applications, we believe the proposed ST-ERF framework can provide valuable insights for designing and optimizing SNN architectures across a broader range of tasks. The code is available at \href{https://github.com/EricZhang1412/Spatial-temporal-ERF}{\faGithub~EricZhang1412/Spatial-temporal-ERF}.

In-context learning (ICL) enables large language models to perform few-shot learning by conditioning on labeled examples in the prompt. Despite its flexibility, ICL suffers from instability -- especially as prompt length increases with more demonstrations. To address this, we treat ICL as a source of weak supervision and propose a parameter-efficient method that disentangles demonstration-induced latent shifts from those of the query. An ICL-based teacher generates pseudo-labels on unlabeled queries, while a student predicts them using only the query input, updating a lightweight adapter. This captures demonstration effects in a compact, reusable form, enabling efficient inference while remaining composable with new demonstrations. Although trained on noisy teacher outputs, the student often outperforms its teacher through pseudo-label correction and coverage expansion, consistent with the weak-to-strong generalization effect. Empirically, our method improves generalization, stability, and efficiency across both in-domain and out-of-domain tasks, surpassing standard ICL and prior disentanglement methods.

The stable periodic patterns present in the time series data serve as the foundation for long-term forecasting. However, existing models suffer from limitations such as continuous and chaotic input partitioning, as well as weak inductive biases, which restrict their ability to capture such recurring structures. In this paper, we propose MoFo, which interprets periodicity as both the correlation of period-aligned time steps and the trend of period-offset time steps. We first design period-structured patches—2D tensors generated through discrete sampling—where each row contains only period-aligned time steps, enabling direct modeling of periodic correlations. Period-offset time steps within a period are aligned in columns. To capture trends across these offset time steps, we introduce a period-aware modulator. This modulator introduces an adaptive strong inductive bias through a regulated relaxation function, encouraging the model to generate attention coefficients that align with periodic trends. This function is end-to-end trainable, enabling the model to adaptively capture the distinct periodic patterns across diverse datasets. Extensive empirical results on widely used benchmark datasets demonstrate that MoFo achieves competitive performance while maintaining high memory efficiency and fast training speed.

Recent advances in AI, driven by Transformer architectures, have achieved remarkable success in language, vision, and multimodal reasoning, and there is growing demand for them to address in-context compositional learning tasks. In these tasks, models solve the target problems by inferring compositional rules from context examples, which are composed of basic components structured by underlying rules. However, some of these tasks remain challenging for Transformers, which are not inherently designed to handle compositional tasks and offer limited structural inductive bias. Inspired by sparse coding, we propose a reformulation of the attention to enhance its capability for compositional tasks. In sparse coding, data are represented as sparse combinations of basic elements, with the resulting coefficients capturing the underlying compositional structure of the input. Specifically, we reinterpret the standard attention block as projecting inputs into outputs through projections onto two sets of learned dictionary atoms: an *encoding dictionary* and a *decoding dictionary*. The encoding dictionary decomposes the input into a set of coefficients, which represent the compositional structure of the input. To enhance structured representations, we impose sparsity on these coefficients. The sparse coefficients are then used to linearly combine the decoding dictionary atoms to generate the output. Furthermore, to assist compositional generalization tasks, we propose estimating the coefficients of the target problem as a linear combination of the coefficients obtained from the context examples. We demonstrate the effectiveness of our approach on the S-RAVEN and RAVEN datasets. For certain compositional generalization tasks, our method maintains performance even when standard Transformers fail, owing to its ability to learn and apply compositional rules.

We present a universal theoretical framework for understanding *long-context language modeling* based on a *bipartite* mutual information scaling law that we rigorously verify in natural language. We demonstrate that bipartite mutual information captures multi-token interactions distinct from and scaling independently of conventional two-point mutual information, and show that this provides a more complete characterization of the dependencies needed for accurately modeling long sequences. Leveraging this scaling law, we formulate the **L**ong-context **L**anguage **M**odeling (**L**$^2$**M**) condition, which lower bounds the necessary scaling of a model's history state—the latent variables responsible for storing past information—for effective long-context modeling. We validate the framework and its predictions on transformer and state-space models. Our work provides a principled foundation to understand long-context modeling and to design more efficient architectures with stronger long-context capabilities, with potential applications beyond natural language.

Long-horizon tasks requiring multi-step reasoning and dynamic re-planning remain challenging for large language models (LLMs). Sequential prompting methods are prone to context drift, loss of goal information, and recurrent failure cycles, while hierarchical prompting methods often weaken cross-level continuity or incur substantial runtime overhead. We introduce ReCAP (Recursive Context-Aware Reasoning and Planning), a hierarchical framework with shared context for reasoning and planning in LLMs. ReCAP combines three key mechanisms: (i) plan-ahead decomposition, in which the model generates a full subtask list, executes the first item, and refines the remainder; (ii) structured re-injection of parent plans, maintaining consistent multi-level context during recursive return; and (iii) memory-efficient execution, bounding the active prompt so costs scale linearly with task depth. Together these mechanisms align high-level goals with low-level actions, reduce redundant prompting, and preserve coherent context updates across recursion. Experiments demonstrate that ReCAP substantially improves subgoal alignment and success rates on various long-horizon reasoning benchmarks, achieving a 32\% gain on synchronous Robotouille and a 29\% improvement on asynchronous Robotouille under the strict pass@1 protocol.

The interpretation of genomic sequences is crucial for understanding biological processes. To handle the growing volume of DNA sequence data, Genomic Foundation Models (GFMs) have been developed by adapting architectures and training paradigms from Large Language Models (LLMs). Despite their remarkable performance in DNA sequence classification tasks, there remains a lack of systematic understanding regarding the training and task-adaptation processes of GFMs. Moreover, existing GFMs cannot achieve state-of-the-art performance on both short and long-context tasks and lacks multimodal abilities. By revisiting pre-training architectures and post-training techniques, we propose **Omni-DNA**, a family of models spanning 20M to 1.1B parameters that supports sequence understanding, long-context genomic reasoning, and natural-language annotation. **Omni-DNA** establishes new state-of-the-art results on 18 of 26 evaluations drawn from Nucleotide Transformer and Genomic Benchmarks. When jointly fine-tuning on biologically related tasks, **Omni-DNA** consistently outperform existing models and demonstrate multi-tasking abilities. To enable processing of arbitrary sequence lengths, we introduce **SEQPACK**—an adaptive compression operator that packs historical tokens into a learned synopsis using a position-aware learnable sampling mechanism, enabling transformer-based models to process ultra-long sequences with minimal memory and computational requirements. Our approach demonstrates superior performance on enhancer-target interaction tasks, capturing distant regulatory interactions at the 450kbp range more effectively than existing models. Finally, we present a new dataset termed **seq2func**, enabling Omni-DNA to generate accurate and functionally meaningful interpretations of DNA sequences, unlocking new possibilities for genomic analysis and discovery.

Predicting accurate future trajectories of pedestrians is essential for autonomous systems but remains a challenging task due to the need for adaptability in different environments and domains. A common approach involves collecting scenario-specific data and performing fine-tuning via backpropagation. However, the need to fine-tune for each new scenario is often impractical for deployment on edge devices. To address this challenge, we introduce TrajICL, an In-Context Learning (ICL) framework for pedestrian trajectory prediction that enables adaptation without fine-tuning on the scenario-specific data at inference time without requiring weight updates. We propose a spatio-temporal similarity-based example selection (STES) method that selects relevant examples from previously observed trajectories within the same scene by identifying similar motion patterns at corresponding locations. To further refine this selection, we introduce prediction-guided example selection (PG-ES), which selects examples based on both the past trajectory and the predicted future trajectory, rather than relying solely on the past trajectory. This approach allows the model to account for long-term dynamics when selecting examples. Finally, instead of relying on small real-world datasets with limited scenario diversity, we train our model on a large-scale synthetic dataset to enhance its prediction ability by leveraging in-context examples. Extensive experiments demonstrate that TrajICL achieves remarkable adaptation across both in-domain and cross-domain scenarios, outperforming even fine-tuned approaches across multiple public benchmarks.

Large language models (LLMs) are increasingly capable of processing long inputs and locating specific information within them, as evidenced by their performance on the Needle in a Haystack (NIAH) test. However, while models excel at recalling surprising information, they still struggle to identify clearly omitted information. We introduce AbsenceBench to assesses LLMs' capacity to detect missing information across three domains: numerical sequences, poetry, and GitHub pull requests. AbsenceBench asks models to identify which pieces of a document were deliberately removed, given access to both the original and edited contexts. Despite the apparent straightforwardness of these tasks, our experiments reveal that even state-of-the-art models like Claude-3.7-Sonnet achieve only 69.6% F1-score with a modest average context length of 5K tokens. Our analysis suggests this poor performance stems from a fundamental limitation: Transformer attention mechanisms cannot easily attend to "gaps" in documents since these absences don't correspond to any specific keys that can be attended to. Overall, our results and analysis provide a case study of the close proximity of tasks where models are already superhuman (NIAH) and tasks where models breakdown unexpectedly (AbsenceBench).