Head pose estimation is important for human computer interaction and driver monitoring, but many image based methods remain too costly for resource constrained deployment. We propose STAG-Net, a structure-aware attention over landmark groups for lightweight head Pose estimation that estimates head pose from facial land...
In 2003, Clark et al. proposed the "Knowledge Plane", a layer of intelligent agents that share rich information about network state in order to collaboratively manage the Internet across administrative boundaries. The technology of the day lacked the two capabilities it demanded most: reasoning and unstructured communi...
Francisco Pereira, Justine Sherry, Pratiksha Thaker· 0 citations
Axis-LoRA is proposed, a per-axis adapter that places four LoRA branches inside the embedding model and combines them via a per-query gate and improves 4-benchmark mean R@10 by $+1.28$ to $+1.56$~pp while training only a small fraction of the base parameters on a small axis-counterfactual training set.
Dohoon Kim, Junho Park, Hyunwoong Bae et al.· Proceedings of the 2026 Conf...· 0 citations
Semantic accuracy is an important dimension of knowledge graph quality. Graph-based scoring methods exploit relational structure, while textual representations allow classifiers to draw on knowledge encoded by pre-trained language models (PLMs). We present GenVer, a generative verifier that scores triples using both th...
Ziang Cui· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
Activation storage is often a bottleneck in sparse autoencoder (SAE) training. We study how many unique activations an SAE needs when its total training budget is fixed. Quality improves rapidly as the buffer grows, then reaches a plateau where replaying the buffer is nearly as effective as using fresh activations thro...
N. Koriagin, Nikita Balagansky, Daniil Gavrilov· 0 citations
Typed decision models choose among a fixed set of answer options in a single forward pass, so unlike generative language models they cannot spend more test-time compute on hard inputs by generating more tokens. Looping a block of layers offers this compute in latent space without adding parameters, but prior work found...
David Berghaus, Arber Zela, Behzad Shomali et al.· 0 citations
As large language models (LLMs) are increasingly used to simulate human behavior, their operational validity is typically assessed through accuracy alone, implicitly treating human behavior as deterministic. We argue that on noisy digital trace data, a model's performance depends not only on predicting the correct outc...
Nils Schwager, Simon M\"unker, Alistair Plum et al.· 0 citations
On-policy distillation (OPD) supplies dense token-level supervision by aligning a student to the teacher's next-token distribution on its own generated rollouts. Existing works mostly implement top-$k$ OPD, applying reverse Kullback-Leibler ($\RKL$) divergence between the teacher's and the student's renormalized distri...
Shuaishuai Zu, Jihao Zhao, Pengfei Li et al.· 0 citations
Selecting a next motion in a populated scene is not just a matter of avoiding what is currently in the way: an action can be locally feasible yet drift onto the road instead of the crosswalk, cut into a stream of crossing pedestrians, or bottleneck a narrow passage. These failure modes are invisible from the current st...
Seong-Eun Hong, JuYeong Hwang, Jinhyun Kim et al.· 0 citations
Diffusion and flow models have recently been extended to language modeling, generating text through continuous denoising in token embedding spaces. Pretrained models provide token representations and contextual prediction capabilities, but improving generation with limited additional training requires an appropriate co...
Time-Series Anomaly Detection (TSAD) is a fundamentally challenging task: it is unsupervised, requires high local precision capabilities, and suffers from limited labelled data. Recent work has explored adapting Large Language Models (LLMs) to time-series via cross-modal transfer. However, existing approaches are poorl...
Large Language Models (LLMs) incur severe memory-access overheads due to the cost of loading large weight matrices and key-value (KV) caches. Analog In-Memory Computing (AIMC) is an emerging solution that enables computation directly on static weights stored in memory, substantially reducing energy and latency. 3D-IMC...
Orhun G\"orkem, Athanasios Vasilopoulos, Georgios Pagonis et al.· 0 citations
