AI Systems

Opening — Why this matters now Training large language models has quietly shifted from an optimization problem into a scheduling problem. As model sizes balloon and GPU clusters grow deeper rather than wider, pipeline parallelism has become unavoidable. Yet most efficiency tricks—parameter freezing included—still behave as if time does not exist. This paper introduces TimelyFreeze, a system-level rethink of parameter freezing that aligns what we freeze with when computation actually happens. Instead of blindly freezing layers based on gradient statistics or heuristics, TimelyFreeze asks a more practical question: which parameters are on the critical path right now? ...

Opening — Why this matters now Enterprises love to say they are “data‑driven.” In practice, they are database‑fragmented. A single natural‑language question — How many customers in California? — may be answerable by five internal databases, all structurally different, semantically overlapping, and owned by different teams. Routing that question to the right database is no longer a UX problem. It is an architectural one. ...

Opening — Why this matters now Neuro‑symbolic AI is having a quiet comeback. While large language models dominate headlines, the systems quietly outperforming them on math proofs, logical deduction, and safety‑critical reasoning all share the same uncomfortable truth: reasoning is slow. Not neural inference—reasoning. The paper behind REASON makes an unfashionable but crucial claim: if we want agentic AI that reasons reliably, interprets decisions, and operates in real time, we cannot keep pretending GPUs are good at symbolic and probabilistic logic. They aren’t. REASON is what happens when researchers finally stop forcing logic to cosplay as linear algebra. ...

Opening — Why this matters now Robotics has quietly entered an awkward phase. Models can see remarkably well and talk impressively about tasks—but when it comes to executing long-horizon, high-precision actions in the physical world, performance still collapses in the details. Grasp slips. Motions jitter. Multimodal uncertainty wins. At the same time, video generation models have undergone a renaissance. Large diffusion-based video models now encode temporal causality, implicit physics, and motion continuity at a scale robotics has never had access to. The obvious question follows: ...

Opening — Why this matters now Multi-agent LLM systems are everywhere: debate frameworks, critic–writer loops, role-based agents, orchestration layers stacked like an over-engineered sandwich. Empirically, they work. They reason better, hallucinate less, and converge on cleaner answers. Yet explanations usually stop at hand-waving: diversity, multiple perspectives, ensemble effects. Satisfying, perhaps—but incomplete. This paper asks a sharper question: why do multi-agent systems reach solutions that a single agent—given identical information and capacity—often cannot? And it answers it with something rare in LLM discourse: a clean operator-theoretic explanation. ...

Opening — Why this matters now Large language models have become remarkably fluent. They explain, summarize, reason, and occasionally even surprise us. But fluency is not the same as adaptability. As AI systems are pushed out of chat windows and into open, messy, real-world environments, a quiet limitation is becoming impossible to ignore: language alone does not teach an agent how to live. ...

Opening — Why this matters now Multimodal recommendation has quietly hit a ceiling. Not because we ran out of data — quite the opposite. Images are sharper, text embeddings richer, and interaction logs longer than ever. The problem is architectural complacency: most systems add modalities, but few truly reason across them. Visual features get concatenated. Text is averaged. Users remain thin ID vectors staring helplessly at semantically over-engineered items. ...

Opening — Why this matters now LLM agents are no longer failing because they cannot reason. They fail because they are trained in worlds that are too small, too brittle, or too artificial to matter. As agents are pushed toward real-world tool use—databases, APIs, enterprise workflows—the limiting factor is no longer model size, but environment quality. This paper introduces EnvScaler, a framework arguing that if you want general agentic intelligence, you must first scale the worlds agents inhabit. ...

Opening — Why this matters now For years, we have treated AI models like polished machines: train once, deploy, monitor, repeat. That worldview is now visibly cracking. The paper you just uploaded lands squarely on this fault line, arguing—quietly but convincingly—that modern AI systems are no longer well-described as static functions. They are processes. And processes remember. ...

Opening — Why this matters now Quantization is no longer a niche optimization; it is the price of admission for deploying large language models at scale. As model sizes balloon and inference budgets stubbornly refuse to follow, post-training quantization (PTQ) has become the default survival strategy. Yet one stubborn problem keeps resurfacing: outliers. A handful of extreme weights—or activations—can quietly wreck an otherwise elegant low‑bit deployment. This paper introduces OptRot, a method that tackles that problem not with more data, more calibration, or more training, but with something almost suspiciously modest: a carefully chosen rotation objective. ...