The paper introduces reverse Item Response Theory (IRT) for analyzing cancer drug‑response data, treating cancer types as latent subjects with resistance ability and drugs as items with evasion difficulty. Using 242,036 measurements from the GDSC2 database, the model estimates cancer‑type‑level in‑vitro resistance and drug‑level broad activity on a shared latent scale. Across four missingness regimes, reverse IRT outperforms simple averaging, achieving higher correlation (Δρ = +0.089 to +0.095 at 60% missingness) and the best Brier score among five methods, with stable classifications for 19 of 28 cancer types and 82% directional agreement in a cross‑platform PRISM replication.
By Jung Min Kang
The paper introduces format‑aware fusion, a method that co‑designs quantization producers with their scale domains and consumer layouts to fully exploit four‑bit floating‑point (FP4) Tensor Cores. Using this approach, the authors pretrain the Llama‑3‑family 8B model on 160 billion tokens, achieving up to 37.9 K tokens/s/GPU—significantly higher than standard bfloat16 or Transformer Engine FP4 baselines. The study demonstrates that FP4 performance depends on the interplay of scaling, operand packing, layout, and execution path, with downstream task rankings diverging from training‑loss rankings.
By Robert Hu
MiLoop is a reinforcement‑learning‑based constructive framework for neural combinatorial optimization that propagates selective memory across rollout steps. By fusing current embeddings with historical memory before attention layers and applying adaptive gated updates afterward, it enables a shallow policy to learn dynamic embeddings without external solution labels or search‑space pruning. Experiments on four combinatorial optimization problems show MiLoop consistently generates high‑quality solutions for instances ranging from 100 to 10 million nodes, demonstrating strong generalization.
By Changliang Zhou, Yuanyao Chen, Rongsheng Chen, Zhiyun Lin, Zhenkun Wang
The paper introduces a particle‑level generative model that uses residual‑quantized full‑event data to enable fast, ML‑based surrogate simulation for collider events. It demonstrates conditional generation from detector‑stable particles, explores scaling across dataset and model sizes, and shows that token‑level loss predicts downstream physical fidelity. The work offers an empirical framework for scalable collider full‑event generation using residual‑quantized representations.
By Dan Godi, Dmitrii Kobylianskii, Eilam Gross
AnchorPrompt is an adaptation technique for large audio‑language models that keeps the base model frozen and learns a single block of prompt vectors inserted at the decoder input. By training these prompts through self‑distillation on diverse audio and text perturbations, the method improves answer consistency and reduces hallucinations across multiple benchmarks. The approach is perturbation‑agnostic at inference, enabling zero‑shot transfer to unseen distortions such as reverberation and choice permutations.
By Pooneh Mousavi, Amir Ivry, Mirco Ravanelli, Cem Subakan
The paper introduces Q-MINO, a Quantization-Aware Minimal-Norm Optimizer designed to improve training of ultra-low-bit neural networks. Q-MINO uses a temporal bundle method that incorporates gradient consensus, state-drift regularization, and an alignment constraint to produce stabilized, minimum-norm update directions. The authors solve the resulting constrained subproblem with a warm-started Frank–Wolfe procedure and provide theoretical convergence guarantees via a stochastic Lyapunov Kurdyka–Łojasiewicz framework, along with numerical experiments demonstrating its effectiveness across various quantization levels.
By Don Li
The paper introduces TANGO, a Token‑Aggregated Nonlinear Gating Operator that blends cross‑token mixing and token‑wise transformation in transformer architectures. By computing a nonlinear gate per source token and averaging these gates for each destination, TANGO forms a source‑conditioned linear operator that improves predictive performance. Experiments on web text, formal mathematics, and code show that full‑prefix TANGO achieves the lowest test negative log‑likelihood across 16 settings, while a narrower variant offers substantial throughput gains with only a modest increase in loss.
By Joshua Nunley
The paper presents a new association rule-based data mining technique for classifying breast cancer, emphasizing early detection. It introduces a weighted classification approach that uses three core algorithms: Rule Generation, Rule Pruning, and Rule Prediction. The method identifies frequent itemsets, prunes rules into major and minor groups, and applies the pruned rules to classify test data, demonstrating feasibility and performance on several samples.
By Ali Alsalama, Ahmed Kubba, Ghaith Jamjoum, Zaher Al Aghbari
CommunityKV is a new framework that treats sparse attention as a community detection problem, building a token graph from $QK^T$ scores and partitioning it into semantically coherent communities. It updates token communities in constant time during streaming decoding, avoiding costly global re‑partitioning. Experiments on Qwen3 and Llama‑3.1 show that CommunityKV can increase end‑to‑end generation throughput by up to 1.25×, and with query‑group graph aggregation up to 1.71×, while maintaining comparable accuracy.
By Joe McKenna, Anastasios Alexandridis, Nathan Susanj, Jing Liu
The paper introduces TDAction, a method for one‑step generative modeling that selects transport targets during training based on a cost reflecting shared‑parameter effort and terminal mismatch. By formulating this as a soft‑terminal control problem, the authors derive a closed‑form Batch Tangent Action‑to‑Go value that captures cross‑sample interactions and can be efficiently implemented with randomized tangent probes. Experiments on ImageNet 256×256 demonstrate that TDAction achieves an FID below 1.1 without distillation.
By Zhangyong Liang, Ying Huang, Haibin Ling
QK-Wanda is a new pruning method that extends Wanda by scoring query and key weights together, using each projection’s deletion cost under an unmasked pre‑RoPE reconstruction objective. It augments each projection’s score with information from the opposite projection, enabling shared pruning budgets without requiring gradients or weight updates. Across 15 models ranging from 0.5 B to 72 B parameters, QK-Wanda reduces reconstruction error by 60 % at 50 % sparsity and 45 % at 80 % compared to Wanda, and yields notable downstream improvements on some models such as Llama 2 70 B.
whyItMatters":"The study demonstrates that coupling query and key pruning criteria can substantially lower reconstruction error and improve downstream performance, highlighting both the potential and limitations of local reconstruction as a predictor of model quality."
By Ivan Ilin, Peter Richt\'arik
Faynt is a family of Transformer policies (10M and 75M parameters) that control all 26 characters in Super Smash Bros. Melee from a single checkpoint. After reinforcement learning, the 10M model wins 98.4% of same‑character games against fourteen specialist and multi‑character releases, and defeats a zero‑delay Slippi‑AI model in all 68 evaluated games. The work details architecture, scaling, hyperparameter transfer, supervised pretraining on 840,000 human replays, post‑training curricula, distillation, and efficient inference, and it releases the weights, benchmark suites, and a platform for automated model tournaments.
By Ali Janati, Nikita Kuzmin, Rohit Swamy, Charles Niu
The paper investigates how teacher signals influence parameter updates in Multi‑Teacher On‑Policy Distillation (MOPD) by analyzing Qwen3‑1.7B and SmolLM3‑3B. It shows that loss averaging, Adam’s first‑moment bias, BF16 rounding, and the choice of averaging rule all shape the gradients and ultimately affect task performance. The study quantifies these effects, revealing, for example, that token‑averaging favors longer responses and that BF16 rounding masks most weight changes.
By Siqi Zhu, Suozhi Huang, Kaixuan Zhang, Yuheng Yang, Zhanyang Jin, Yihang Sun, Jiaxuan You
The paper presents a system for the IEEE BigData 2026 Cup on Explainable Suicide Risk Assessment on Social Media. It tackles three tasks—risk-level classification, evidence phrase extraction, and multi-label factor identification—using Qwen2.5-Instruct models adapted with quantized low-rank adaptation (QLoRA) and an answer-masked causal language-model objective. The final system achieved a composite score of 0.7738, with 0.8089 on Task 1 and 0.6919 on Task 2, demonstrating that task‑specific training and tailored aggregation improve performance across the three tasks.
By Xuan Zhong Feng, Geoffrey Martin, Hexin Dong, Yifan Peng
The paper introduces LAST, a Looped Audio Spectrogram Transformer that processes all tokens once and then reuses the same blocks to refine only the class token over fixed audio features, making subsequent passes inexpensive. On AudioSet, a ten‑pass LAST outperforms a twelve‑layer sequential transformer by 2.1% relative mean average precision while using 49.4% fewer parameters, 42% fewer MACs, and achieving 9.8% higher throughput. Increasing the pass count from two to ten improves accuracy with only a 1.2% increase in computation, and the model shows enhanced robustness to temporal masking and other auditory augmentations across music, environmental, and event sound classification tasks.
By Haider Al-Tahan, Sean O'Brien, Anastasia Razdaibiedina, N. Apurva Ratan Murty
The paper introduces temporal self‑distillation for reinforcement learning with verifiable rewards (RLVR), proposing that a policy can learn from a stronger future checkpoint of itself. Two methods—Near‑Future Policy Optimization (NPO) and Near‑Future Policy Distillation (NPD)—use verified future‑self trajectories and token‑level transfer, respectively, while AutoNPO adaptively selects the optimal future checkpoint. Experiments on eight image‑text benchmarks show that near‑future teachers yield higher performance than far‑future ones, indicating that the balance between new capability and learner compatibility is key.
By Chuanyu Qin, Chenxu Yang, Qingyi Si, Naibin Gu, Dingyu Yao, Zheng Lin, Peng Fu, Nan Duan, Jiaqi Wang
ConQuR introduces a lightweight post‑training rotation calibration for large language model activation quantization. By learning orthogonal rotations that align normalized activations with the corners of an inscribed hypercube, the method distributes activation energy evenly and can be updated online without storing activations. Experiments on Llama‑2 and Llama‑3 models (3B–70B) show competitive or improved perplexity and reasoning performance while avoiding costly training or large offline storage.
By Chayne Thrash, Ali Abbasi, Soheil Kolouri
The paper proposes a sensitivity‑aware residual‑stream pruning method for large language models that goes beyond minimizing activation reconstruction error. By using a second‑order approximation of output KL divergence, the authors derive a spectral upper bound that selects pruning subspaces based on both activation covariance and output sensitivity, enabling efficient eigendecomposition. Experiments on instruction‑tuned language models show that this approach consistently reduces calibration KL divergence, improves perplexity, and enhances downstream task performance across various compression levels.
By Chayne Thrash, Kevin Chen, Soheil Kolouri
FedFit introduces a federated fine‑tuning framework for large language models that reduces communication overhead by using a disjoint shared vector‑bank parameterization to reconstruct adapter matrices from two compact global vector banks. It resolves the aggregation dilemma between Sum‑of‑Products and Product‑of‑Sums through an alternating optimization schedule that alternates between accurate single‑bank updates and joint updates corrected by a Residual Spectral Aggregation mechanism. The method also incorporates blockwise quantization with client‑side error feedback and provides theoretical convergence guarantees, achieving perplexity comparable to standard federated LoRA while delivering up to 100× higher compression ratios on Qwen2.5 models.
By Hang Zou, Chao Zhang, Yuzhi Yang, Yu Tian, Samson Lasaulce, M\'erouane Debbah
CrossGMN introduces a graph metanetwork that processes a trained source network and an initialized target network simultaneously, enabling equivariant cross‑architecture weight‑space transformations. By preserving symmetry through cross‑network message passing, CrossGMN can refine target network initializations while remaining invariant to source permutations and equivariant to target permutations. Experiments demonstrate that CrossGMN accelerates knowledge distillation, transfers across datasets without retraining, and unifies compression from diverse source architectures into a common target architecture.
By Adir Dayan, Yam Eitan, Haggai Maron