An interactive world model must follow the user's actions, remember the places it has shown, and stream in real time. The tension is structural: control wants a short horizon, memory wants an unbounde...
arXiv:2608.23565v1 Announce Type: new Abstract: An interactive world model must follow the user's actions, remember the places it has shown, and stream in real time. The tension is structural: contro...
arXiv:2609.40222v1 Announce Type: new Abstract: When a camera revisits a previously observed region, a video world model should reproduce what was there before. This requires both remembering past ob...
Memory Forcing is a new few‑step streaming method for autoregressive video diffusion that keeps a diverse mid‑horizon history without enlarging the KV cache. It partitions the cache into Archive, Working, and sink banks, and uses Bank‑aware RoPE to keep each bank distinguishable even as absolute temporal indices drift. Experiments show that at 1.3B parameters it outperforms other methods on longer clips, maintains subjects and scenes when they leave and re‑enter the window, and scales to a 5B model that produces more realistic, dynamic videos.
arXiv:2609.00291v1 Announce Type: new Abstract: Streaming video understanding requires answering questions that arrive at arbitrary moments over an unbounded video stream. Existing systems primarily...
arXiv:2606. 16353v1 Announce Type: cross Abstract: Streaming video understanding models must answer queries at any moment during an ongoing stream, using only what they have observed so far and under fixed memory and computation budgets.
arXiv:2609.39096v1 Announce Type: new Abstract: Autoregressive video diffusion supports streaming generation and interactive control, but its KV cache grows with the generated history. Existing compr...
arXiv:2609.06872v1 Announce Type: new Abstract: When a user asks an assistant to forget a record, the test is whether the memory now matches the state it would hold if the record had never been store...
The paper investigates how block‑diffusion language models can use a constant‑size cache to enable efficient parallel decoding. By employing sequence mixers that summarize completed blocks into a reusable state and a block‑causal training objective, the authors pretrain three 3B block‑diffusion denoisers (attention, Mamba, and hybrid) on 300 B tokens. The resulting state‑space cache remains O(1) in memory and latency regardless of context length, yielding significant speed‑up and memory savings compared to traditional attention‑based caches, especially at very long sequences.
The paper introduces LRE (Learned Relevance Eviction), a lightweight, CPU‑only, language‑model‑free scorer that learns which parts of an agent’s interaction history are task‑critical and preserves them verbatim. In experiments, LRE matches or surpasses baseline eviction policies on accuracy‑cost trade‑offs, recovers 93% of full‑history accuracy, reduces worst‑case prompt size by 52%, and outperforms dense and token‑pruning encoders in conversational memory while being 295–1569× smaller. The method also achieves superior budgeted answer quality on LoCoMo reading and can be trained annotation‑free, recovering 95% of supervised scorer performance.
arXiv:2606. 31495v1 Announce Type: new Abstract: We study a single idea across two settings: that a prediction-error signal, computed by a small predictor over the latent space of a frozen encoder, can serve both as a gate on plasticity and as a substrate for metacognition.
arXiv:2607. 24667v1 Announce Type: new Abstract: A language model with a bounded working memory must repeatedly decide which stored items to keep.