arXiv:2601.20447v1 Announce Type: new Abstract: Enabling natural communication through brain-computer interfaces (BCIs) remains one of the most profound challenges in neuroscience and neurotechnology. While existing frameworks offer partial solutions, they are constrained by oversimplified semantic representations and a lack of interpretability. To overcome these limitations, we introduce Semantic Intent Decoding (SID), a novel framework that […]
Discrete Variational Autoencoding via Policy Search
arXiv:2509.24716v2 Announce Type: replace-cross Abstract: Discrete latent bottlenecks in variational autoencoders (VAEs) offer high bit efficiency and can be modeled with autoregressive discrete distributions, enabling parameter-efficient multimodal search with transformers. However, discrete random variables do not allow for exact differentiable parameterization; therefore, discrete VAEs typically rely on approximations, such as Gumbel-Softmax reparameterization or straight-through gradient […]
CtrlCoT: Dual-Granularity Chain-of-Thought Compression for Controllable Reasoning
arXiv:2601.20467v1 Announce Type: new Abstract: Chain-of-thought (CoT) prompting improves LLM reasoning but incurs high latency and memory cost due to verbose traces, motivating CoT compression with preserved correctness. Existing methods either shorten CoTs at the semantic level, which is often conservative, or prune tokens aggressively, which can miss task-critical cues and degrade accuracy. Moreover, combining […]
Dual-objective Language Models: Training Efficiency Without Overfitting
arXiv:2512.14549v2 Announce Type: replace-cross Abstract: This paper combines autoregressive and masked-diffusion training objectives without any architectural modifications, resulting in flexible language models that outperform single-objective models. Autoregressive modeling has been a popular approach, partly because of its training efficiency; however, that comes at the cost of sensitivity to overfitting. On the other hand, masked-diffusion models […]
Normative Equivalence in human-AI Cooperation: Behaviour, Not Identity, Drives Cooperation in Mixed-Agent Groups
arXiv:2601.20487v1 Announce Type: new Abstract: The introduction of artificial intelligence (AI) agents into human group settings raises essential questions about how these novel participants influence cooperative social norms. While previous studies on human-AI cooperation have primarily focused on dyadic interactions, little is known about how integrating AI agents affects the emergence and maintenance of cooperative […]
LAPS: A Length-Aware-Prefill LLM Serving System
arXiv:2601.11589v2 Announce Type: replace-cross Abstract: LAPS identifies and disaggregates requests with different prompt lengths in LLM serving to reduce TTFT latency. While recent systems have decoupled the prefill and decode stages to improve throughput, they still rely on unified scheduling policies that fail to adapt to heterogeneous workload characteristics. We observe that prompt-length variations lead […]
PathWise: Planning through World Model for Automated Heuristic Design via Self-Evolving LLMs
arXiv:2601.20539v1 Announce Type: new Abstract: Large Language Models (LLMs) have enabled automated heuristic design (AHD) for combinatorial optimization problems (COPs), but existing frameworks’ reliance on fixed evolutionary rules and static prompt templates often leads to myopic heuristic generation, redundant evaluations, and limited reasoning about how new heuristics should be derived. We propose a novel multi-agent […]
Online Risk-Averse Planning in POMDPs Using Iterated CVaR Value Function
arXiv:2601.20554v1 Announce Type: new Abstract: We study risk-sensitive planning under partial observability using the dynamic risk measure Iterated Conditional Value-at-Risk (ICVaR). A policy evaluation algorithm for ICVaR is developed with finite-time performance guarantees that do not depend on the cardinality of the action space. Building on this foundation, three widely used online planning algorithms–Sparse Sampling, […]
Conditional PED-ANOVA: Hyperparameter Importance in Hierarchical & Dynamic Search Spaces
arXiv:2601.20800v1 Announce Type: cross Abstract: We propose conditional PED-ANOVA (condPED-ANOVA), a principled framework for estimating hyperparameter importance (HPI) in conditional search spaces, where the presence or domain of a hyperparameter can depend on other hyperparameters. Although the original PED-ANOVA provides a fast and efficient way to estimate HPI within the top-performing regions of the search […]
Dialogical Reasoning Across AI Architectures: A Multi-Model Framework for Testing AI Alignment Strategies
arXiv:2601.20604v1 Announce Type: new Abstract: This paper introduces a methodological framework for empirically testing AI alignment strategies through structured multi-model dialogue. Drawing on Peace Studies traditions – particularly interest-based negotiation, conflict transformation, and commons governance – we operationalize Viral Collaborative Wisdom (VCW), an approach that reframes alignment from a control problem to a relationship problem […]
Post-Training Fairness Control: A Single-Train Framework for Dynamic Fairness in Recommendation
arXiv:2601.20848v1 Announce Type: cross Abstract: Despite growing efforts to mitigate unfairness in recommender systems, existing fairness-aware methods typically fix the fairness requirement at training time and provide limited post-training flexibility. However, in real-world scenarios, diverse stakeholders may demand differing fairness requirements over time, so retraining for different fairness requirements becomes prohibitive. To address this limitation, […]
Harder Is Better: Boosting Mathematical Reasoning via Difficulty-Aware GRPO and Multi-Aspect Question Reformulation
arXiv:2601.20614v1 Announce Type: new Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) offers a robust mechanism for enhancing mathematical reasoning in large models. However, we identify a systematic lack of emphasis on more challenging questions in existing methods from both algorithmic and data perspectives, despite their importance for refining underdeveloped capabilities. Algorithmically, widely used Group Relative […]