ICML 2026 论文列表

Audio provides critical situational cues, yet current Audio Language Models (ALMs) face an attention bottleneck in long-form recordings where dominant background patterns can dilute rare, salient events. We introduce NAACA, a training-free NeuroAuditory Attentive Cognitive Architecture that reframes attention allocation as an auditory salience filtering problem. At its core is OWM, a neuro-inspired Oscillatory Working Memory that maintains stable attractor-like states and triggers higher-cognition ALM processing only when adaptive energy fluctuations signal perceptual salience, triggering higher-level reasoning. On XD-Violence, NAACA improves AudioQwen’s average precision (AP) from 53.50\% to 70.60\% while reducing unnecessary ALM invocations. Furthermore, qualitative case studies on the Urban Soundscapes of the World (USoW) dataset show that OWM captures novel events and subcategory shifts while remaining robust to transient pauses and ambient urban noise.

Recent advances in audio deepfake detection have been driven by increasingly large speech foundation models and growing amounts of synthetic data. Despite strong benchmark performance, it remains unclear how detection capability scales with model capacity and training data under realistic deployment conditions involving distribution shift, signal corruption, and unseen synthesis pipelines. In this work, we present the first systematic study of scaling laws in post-training audio deepfake detection, focusing on fine-tuning regimes rather than large-scale pretraining. Using a controlled family of speech foundation models with shared architecture and pretraining, we analyze how detection performance, robustness, and generalization evolve as a function of model size and training data scale. Our results reveal a fundamental asymmetry between performance scaling and robustness scaling in audio deepfake detection, suggesting increasing model capacity alone is insufficient for achieving reliable real-world generalization.

We present SoftMatcha 2, an ultra-fast and flexible search algorithm that enables search over trillion-scale natural language corpora in under 0.3 seconds while allowing semantic variations in the form of substitution, insertion, and deletion. Our approach employs string matching based on suffix arrays that scales well with corpus size, and represents words as vectors, which underpin its semantic flexibility. To mitigate the combinatorial explosion induced by the semantic relaxation of queries, our method is built on two key algorithmic ideas: dynamic corpus-aware pruning and fast exact lookup enabled by a disk-aware design. We theoretically analyze the efficiency of the proposed method, indicating that it can mitigate exponential growth in the search space. Empirically, on FineWeb-Edu (Lozhkov et al., 2024) (1.4T tokens), it attains substantially lower search latency than existing methods: infini-gram (Liu et al., 2024), infini-gram mini (Xu et al., 2025), and SoftMatcha (Deguchi et al., 2025). As a practical application, our method uncovers benchmark contamination in training corpora that existing approaches miss, and it also benefits information retrieval and paraphrase detection. We also provide an online demo of fast, soft search across corpora in seven languages.

Large Language Models (LLMs) have catalyzed vibe coding, where users leverage LLMs to generate and iteratively refine code through natural language interactions until it passes their *vibe check*. *Vibe check* reflects human preference and goes beyond functionality: the solution should feel right, read cleanly, preserve intent, and remain correct. However, current code evaluation remains anchored to pass@k and captures only functional correctness, overlooking non-functional instructions that users routinely apply. In this paper, we hypothesize that instruction following is the missing piece underlying *vibe check* besides functional correctness. To quantify models' code instruction-following capabilities with measurable signals, we present VeriCode, a taxonomy of 30 verifiable code instructions together with deterministic verifiers. We use the taxonomy to augment established evaluation suites, resulting in **SWE-IF**, a testbed to assess both instruction following and functional correctness. Evaluating 31 LLMs, we show that even the strongest models struggle to comply with multiple instructions and exhibit functional regression. Most importantly, a composite score of functional correctness and instruction following correlates best with human preference, with instruction following emerging as the primary differentiator among LLMs. Our code, data, and taxonomy are available at https://github.com/maszhongming/SWE-IF.

Recent advances in LipSync generation technology have led to the creation of highly realistic videos, posing severe societal risks. However, existing defense strategies struggle against LipSync forgeries, as state-of-the-art generative models not only optimize for the lip synchronization but also significantly eliminate visual artifacts, resulting in the lack of key detection signals. Inspired by the inherent biological coupling between lip movements and head poses in natural speech, we observe that generative models fundamentally disrupt this global coordination when optimizing for local lip motion. In this paper, we propose LipDA, a novel framework for joint LipSync Detection and Attribution, which takes advantage of the inconsistency between head and lip. For detection, the framework learns to quantify this discrepancy by contrasting lip and pose features from authentic versus forged videos. For attribution, our method is designed to capture the unique temporal dynamics and audio-visual synchronization patterns that act as generative fingerprints, enabling source tracing. To validate our approach, we conduct extensive experiments on two challenging LipSync benchmarks as well as on our own proposed large-scale and multi-generator dataset, LipSyncBench-A. LipDA achieves over 97% AUC in detection and 97.5% accuracy in model attribution, significantly outperforming existing methods.

Supervised fine-tuning (SFT) and reinforcement learning with verifiable rewards (RLVR) are two widely used post-training paradigms for improving the reasoning ability of large language models (LLMs). Recent methods attempt to integrate SFT and RLVR in a single stage by reweighting or scheduling their objectives. However, such coupling can be counterproductive because supervised updates are not uniformly beneficial for reward optimization. To address this, we propose BRIDGE, a scalable framework in which SFT learns to supervise RL by selectively transferring knowledge that improves reward optimization. Specifically, BRIDGE alternates two updates at each meta-training step: a base-model update that fuses the SFT and RL gradients, and an update to a lightweight low-rank adapter (LoRA) that coordinates the two objectives by maximizing a cooperative-gain signal, defined as the reward of joint SFT–RL training over an RL-only baseline. Across five mathematical reasoning benchmarks, BRIDGE consistently outperforms two-stage cold start, naive mixing, and representative single-stage integration baselines, yielding over three points average absolute improvement and more stable training dynamics. We further show that BRIDGE extends to logical reasoning and generalizes out-of-distribution to code and science without additional training, while staying robust under noisy rewards.

Training autonomous web agents is fundamentally limited by the environments they learn from: real-world websites are unsafe to explore, hard to reset, and rarely provide verifiable feedback. We propose VeriEnv, a framework that treats language models as environment creators, automatically cloning real-world websites into fully executable, verifiable synthetic environments. By exposing controlled internal access via a Python SDK, VeriEnv enables agents to self-generate tasks with deterministic, programmatically verifiable rewards, eliminating reliance on heuristic or LLM-based judges. This design decouples agent learning from unsafe real-world interaction while enabling scalable self-evolution through environment expansion. Through experiments on web agent benchmarks, we show that agents trained with VeriEnv generalize to unseen websites, achieve site-specific mastery through self-evolving training, and benefit from scaling the number of training environments.

Operator splitting methods are at the foundation of many numerical solvers for partial differential equations. In parallel, unrolled and hybrid learning-based architectures have been introduced to enhance classical solvers, but their design is rarely linked to the underlying problem structure. In this work, we propose a unifying framework that explicitly links operator splitting algorithms from optimization with unrolled hybrid architectures. We show that each operator splitting scheme naturally defines an unrolled architecture, which recovers a wide range of existing plug-and-play and hybrid models as special cases. Using this framework, we design new unrolled hybrid architectures and validate them on benchmark fluid dynamics simulations, where they achieve improved accuracy and stability.

Emotional expression in human speech is nuanced and compositional, often involving multiple, sometimes conflicting, affective cues that may diverge from linguistic content. In contrast, most expressive text-to-speech (TTS) systems enforce a single utterance-level emotion, collapsing affective diversity and suppressing mixed or text–emotion–misaligned expression. While activation steering via latent direction vectors offers a promising solution, it remains unclear whether emotion representations are linearly steerable in TTS, where steering should be applied within hybrid TTS architectures, and how such complex emotion behaviors should be evaluated. This paper presents the first systematic analysis of activation steering for emotional control in hybrid TTS models, introducing a quantitative, controllable steering framework, and multi-rater evaluation protocols that enable composable mixed-emotion synthesis and reliable text–emotion mismatch synthesis. Our results demonstrate, for the first time, that emotional prosody and expressive variability are primarily synthesized by the TTS language module instead of the flow-matching module, and also provide a lightweight steering approach for generating natural, human-like emotional speech.

Biological and neuromorphic recurrent neural networks (RNNs) are subject to spatial and temporal locality constraints on the information that can plausibly be used during learning. A common strategy to satisfy these constraints is to modify gradient descent by neglecting non-local terms to varying degrees, as in random feedback local online (RFLO) learning and truncated backpropagation through time (tBPTT). However, the learning dynamics of these algorithms, and how they compare with BPTT, remain poorly understood. We apply dynamical systems theory to data-aligned linear RNNs---whose dynamics can be separated into orthogonal modes---to compare stationary solutions, stability properties, and convergence rates, finding qualitatively distinct behaviour for RFLO versus BPTT and one-step tBPTT. We further observe that the solutions learned by RFLO are restricted to low-rank perturbations of initial parameters, a result which holds beyond the data-aligned setting. Our work provides analytical insight into how locality constraints shape learning dynamics, with implications for neuroscientific models of learning and alternative optimization approaches for RNNs.

Scaling test-time compute via long Chain-of-Thought unlocks remarkable gains in reasoning capabilities, yet it faces practical limits due to the linear growth of KV cache and quadratic attention complexity. In this paper, we introduce AccordionThinking, an end-to-end framework where LLMs learn to self-regulate the granularity of the reasoning steps through dynamic summarization. This mechanism enables a Fold inference mode, where the model periodically summarizes its thought process and discards former thoughts to reduce dependency on historical tokens. We apply reinforcement learning to incentivize this capability further, uncovering a critical insight: the accuracy gap between the highly efficient Fold mode and the exhaustive Unfold mode progressively narrows and eventually vanishes over the course of training. This phenomenon demonstrates that the model learns to encode essential reasoning information into compact summaries, achieving effective compression of the reasoning context. Our AccordionThinker demonstrates that with learned self-compression, LLMs can tackle complex reasoning tasks with minimal dependency token overhead without compromising solution quality, and it achieves a 3× throughput while maintaining accuracy on a 48GB GPU memory configuration, while the structured step summaries provide a human-readable account of the reasoning process.

Mixture-of-Experts (MoE) models achieve efficient scaling through sparse expert activation, but often suffer from suboptimal routing decisions due to distribution shifts in deployment. While existing test-time adaptation methods could potentially address these issues, they primarily focus on dense models and require access to external data, limiting their practical applicability to MoE architectures. However, we find that, instead of relying on reference data, we can optimize MoE expert selection on-the-fly based only on input context. As such, we propose *a data-free, online test-time framework* that continuously adapts MoE routing decisions during text generation without external supervision or data. Our method cycles between two phases: During the prefill stage, and later in regular intervals, we optimize the routing decisions of the model using self-supervision based on the already generated sequence. Then, we generate text as normal, maintaining the modified router until the next adaption. We implement this through lightweight additive vectors that only update router logits in selected layers, maintaining computational efficiency while preventing over-adaptation. The results show consistent performance gains on challenging reasoning tasks while maintaining robustness to context shifts. For example, our method achieves a 5.5\% improvement on HumanEval with OLMoE. Furthermore, owing to its plug-and-play property, our method complements existing test-time scaling techniques, e.g., achieving 6\% average gains when incorporated with self-consistency on DeepSeek-V2-Lite.

Advances in AIGC technologies have enabled the synthesis of highly realistic audio deepfakes capable of deceiving human auditory perception. Although numerous audio deepfake detection (ADD) methods have been developed, most rely on local temporal/spectral features or pairwise relations, overlooking high-order interactions (HOIs). HOIs capture discriminative patterns that emerge from multiple feature components beyond their individual contributions. We propose HyperPotter, a hypergraph-based framework designed to capture high-order relations associated with synergistic patterns through clustering-based hyperedges with class-aware prototype initialization. Extensive experiments on 13 test sets show that HyperPotter improves over the baseline on 11 sets, yielding an average relative EER reduction of 12.68\% across all test sets and 22.15\% on the improved sets. These results demonstrate strong cross-scenario generalization, while also revealing robustness limits under severe codec or channel distortion.

Self-supervised learning (SSL) has significantly advanced acoustic representation learning. However, most existing models are optimised for either speech or audio event understanding, resulting in a persistent gap between these two domains. We address this gap with SPEAR (SPEech and Audio Representations), a self-supervised framework that distils complementary knowledge from a speech-focused SSL teacher and a general-audio SSL teacher into a single unified model. SPEAR applies multi-codebook vector quantisation to continuous teacher representations to produce fine-grained discrete tokens that capture both semantic and acoustic information. To effectively integrate these heterogeneous representations, SPEAR jointly predicts them given a masked input with an asymmetric pre-training loss. We further improve robustness in complex sound scenes through a novel token mixing mechanism. Extensive experiments demonstrate that SPEAR consistently outperforms existing unified speech and audio models. SPEAR establishes a new state-of-the-art on the SUPERB benchmark, surpassing WavLM Large on 12 of 15 tasks, while achieving competitive performance on the HEAR benchmark. These results position SPEAR as a versatile foundation for general-purpose speech and audio representation learning. The code and pre-trained models will be released.

Query-based universal sound separation is fundamental to intelligent auditory systems, aiming to isolate specific sources from mixtures. Despite recent advances, existing methods continue to suffer from residual interference in complex acoustic scenes. This performance limitation stems largely from a data bottleneck: in-the-wild datasets contain weak labels and severe co-occurrence of events. These flaws induce models to learn spurious correlations between background noise and target categories instead of robust acoustic features. To address this, we propose an automated pipeline that eliminates co-occurrence of events by mining high-purity single-event segments from in-the-wild datasets via a semantically consistent synthesis protocol. Utilizing this pipeline, we constructed Hive, a high-quality synthetic dataset comprising 2.4k hours of raw audio. Experimental results demonstrate that, compared with the state-of-the-art model SAM-Audio which was trained on a huge dataset $\sim$500 times larger than Hive, certain open-source models trained on Hive achieve competitive separation accuracy and perceptual quality. Moreover, these models exhibited remarkable zero-shot generalization on out-of-distribution evaluation benchmarks. These findings highlight that prioritizing purity of supervised signals enables significant data efficiency, offering a new paradigm for training robust auditory foundation models with reduced computational costs. Code and dataset are available at https://cslikai.cn/Hive.

Audio large language models (Audio LLMs) demonstrate strong performance on speech understanding tasks, yet their ability to understand paralinguistic information remains limited. To systematically quantify this issue, we introduce **VoxParadox**, an adversarial benchmark with 2,000 verified examples, spanning 10 paralinguistic tasks, created with controlled speech synthesis to intentionally mismatch transcript claims and speaking style, enabling direct measurement of speech paralinguistic understanding. Evaluation of a diverse set of Audio LLMs reveals consistently low accuracy on acoustic ground truth and a strong tendency to follow language-implied (incorrect) answers. To understand the cause of this gap, we perform layer-wise probing and find that (i) paralinguistic cues can degrade in deeper encoder layers and at the encoder--LLM interface, and (ii) even when such cues are available in audio tokens, the language model frequently ignores them. To address these problems, we propose **Prompt-Conditioned Layer Mixer (PCLM)**, which adaptively combines information from multiple audio layers based on the input prompt, and pair it with **Direct Preference Optimization (DPO)** to explicitly prefer acoustically supported options over language-implied alternatives. These methods substantially improve Audio LLM paralinguistic understanding, improving Audio Flamingo 3 from **17.40%** to **65.20%** on VoxParadox, and from **37.74%** to **54.78%** on MMSU paralinguistic subset. Our project page is available at https://voxparadox.github.io/.

To handle ambiguous and open-ended requests, Large Language Models (LLMs) are increasingly trained to interact with users to surface intents they have not yet expressed (e.g., ask clarification questions). However, users are often ambiguous because they have not yet formed their intents: they must observe and explore outcomes to discover what they want. Simply asking "what kind of tone do you want?" fails when users themselves do not know. We introduce DiscoverLLM, a novel and generalizable framework that trains LLMs to help users form and discover their intents. Central to our approach is a novel user simulator that models cognitive state with a hierarchy of intents that progressively concretize as the model surfaces relevant options---where the degree of concretization serves as a reward signal that models can be trained to optimize. Resulting models learn to collaborate with users by adaptively diverging (i.e., explore options) when intents are unclear, and converging (i.e., refine and implement) when intents concretize. Across proposed interactive benchmarks in creative writing, technical writing, and SVG drawing, DiscoverLLM achieves over 10% higher task performance while reducing conversation length by up to 40%. In a user study with 75 human participants, DiscoverLLM improved conversation satisfaction and efficiency compared to baselines.

In modern software development, particularly in emerging ``vibe coding'' paradigms, project implementation increasingly begins with visual interactions between users and AI coding assistants, where system architectures are communicated through visual designs before coding. This visual-first approach necessitates AI systems capable of interpreting diagrams across multiple programming languages. However, the development of such systems is severely hindered by the lack of large-scale multimodal training data and evaluation benchmarks. To address these limitations, we present M²C-INSTRUCT, a comprehensive multilingual multimodal instruction-tuning dataset containing over 13.1M samples across 50+ programming languages, designed for visual understanding and diagram interpretation in code generation tasks. We validate our dataset by training M²-CODER, a multilingual multimodal software developer that successfully integrates visual design inputs with textual instructions. We also introduce M²EVAL, a novel multilingual evaluation benchmark for multimodal code generation performance. Experiments show our 7B M²-CODER, performs on par with much larger 70B+ models, confirming the quality and effectiveness of our M²C-INSTRUCT. Together, M²C-INSTRUCT, M²-CODER, and M²EVAL provide essential infrastructure for visual-assisted programming in vibe-coding and visual-interactive development workflows.

Current multimodal large language models (LLMs) process audio as a mono stream, ignoring the rich spatial information essential for embodied AI. Conversely, existing spatial audio models are constrained to fixed microphone geometries, preventing their deployment across diverse devices. We present **PhaseCoder**, a transformer-only spatial audio encoder that is inherently agnostic to microphone geometry. By taking raw multichannel audio and microphone coordinates as inputs, PhaseCoder performs accurate localization and produces robust spatial embeddings. We demonstrate that the Gemma 3n LLM can be fine-tuned to process and reason over the "Spatial Audio Tokens" produced by our encoder. PhaseCoder achieves state-of-the-art results on microphone-invariant localization benchmarks and, for the first time, enables an LLM to perform complex spatial reasoning and targeted transcription tasks from an arbitrary microphone array.